Research Design & Methodology

This is a module on Research Methods and Design. The module guides the student step by step in the development and design of a research project.


Hire a Specialist

Get Help With Your Dissertation Or Thesis, Today

Chapter 1: Research Design & Methodology

Working on dissertations or thesis for the first time may make you feel overwhelmed. However, obtaining and analysing data, using research methods, and doing research seems to continue forever. A research design, for instance, is a comprehensive structure and plan for answering the research project’s question. On the other hand, a research strategy is a technique utilized to carry out that plan. To answer various questions, various approaches can be used. Although research design and methods are distinct, they are closely related because sound research design ensures that the information you gather will enable you to address your research question more comprehensively.

Research Methodology

The center stage for any scholarly research work and specifically a dissertation is simply the methodology section. However, it focuses more precisely on the methods the researcher uses when creating a study to provide reliable results that satisfy the study’s goals and objectives.

How did the researcher decide, for instance;

  • Which data to gather and which to ignore in research
  • From whom to gather the data; this is known as sampling design
  • Data collection methods are the means of gathering it.
  • How to assess it is also known as data analysis.

A robust methodology chapter is crucial for any dissertation or thesis since it explains the methodology choices made and justifies them. The methodology chapter must demonstrate how the techniques and procedures chosen are the best fits for the study’s aims and objectives and will yield trustworthy data in order to support the design decisions. A good approach produces sound results from a scientific standpoint compared to a substandard procedure.

Methodologies using qualitative, quantitative, and combined methods

Researchers can analyse and relate their work in a variety of ways. Whether these techniques emphasize words, figures, or both is what sets them apart. Despite being oversimplified, this is an excellent place to start when comprehending something. Quantitative and qualitative research methodologies are the two main types. A third methodology that combines the two approaches is becoming more popular to enhance and support research findings. The quantitative method, which includes scientific inquiry at its core, analyses data using statistical tools. A qualitative technique is often used when the research’s goals and objectives are exploratory. To find out what people think of a presidential candidate or a current incident, for instance, one can use a qualitative technique. Compared to quantitative procedures, qualitative approaches use descriptive narratives to analyse data. Quantitative research methods have a long history and are used most frequently in the research literature.

¬†Quantitative research, on the other hand, employs numbers to test hypotheses, make predictions based on measured amounts, and eventually characterize an event using numbers. The researcher can use complex and compelling statistical tests by employing data to ensure that the results have a statistical connection and are not just accidental observations. When the research’s goals and objectives are to provide confirmation, a quantitative technique is frequently used. A quantitative technique can be used, for instance, to evaluate a set of hypotheses or establish the connection between two factors, such as personality type and the chance of committing a crime. The mixed-method technique, as you may guess, seeks to combine the finest components of qualitative and quantitative methodologies to integrate views and give a full picture.

The main sampling design approaches

A crucial step in sample design is choosing your sources for data collecting. The two main categories of sampling designs are probability and non-probability, and there are several alternate sample options. You must carefully consider how you will choose a sample that is typical of the entire population if you want to be able to make meaningful inferences from your data. Probability sampling’s a crucial element of random selection that enables you to make reliable statistical inferences about the entire population.

Due to the entirely random nature of your sample, the findings of your study may be applicable to the entire population. To put it another way, you can forecast the precise results everywhere rather than attempting to collect input from the whole group, which is typically impractical for big groups. Non-probability sampling incorporates non-random selection based on convenience or other characteristics, making data collecting easier than using a random sample. Interviewing or polling individuals you already know, such as friends, family, or co-workers, is what is meant by using a convenience sample, as opposed to a truly random sample, which might be difficult owing to resource limits. The results of non-probability sampling are typically not generalizable. In the area of your essay or thesis devoted to methodology, you must carefully explain how you chose your sample.

The main methods of data collection

To answer the research question, test the hypothesis (if you’re using a deductive method), and analyze the results, you must collect data from all relevant sources. The development of technology increased the demand for educators more than ever before. Unfortunately, this has also happened due to a flood of information, some of which may be cumbersome. Nevertheless, valuable insights and time-wasting misinformation can be obtained using the proper data collection methodology. There are numerous alternatives for how you might go about gathering data for your project. However, the following types can be used to classify these choices:

  • Focus groups and group interviews; unstructured, semi-structured, and structured interviews
  • Surveys conducted offline or online
  • Observations
  • Records and paperwork
  • Studying cases

Your overall research goals and objectives, as well as logistical concerns and financial constraints, will all have an impact on the data collecting method you choose. For instance, if your study is exploratory, qualitative methods like focus groups and interviews might be a good fit. On the other hand, if your research aims to quantify particular factors or test hypotheses, large-scale surveys that produce enormous volumes of numerical data would probably be preferable.

The main data analysis methods

Depending on whether the study is qualitative or quantitative, the methods for data analysis may be divided into different categories. The following methods are frequently used for assessing data from qualitative research:

  • Qualitative content analysis
  • Thematic analysis
  • Discourse evaluation
  • Narrative evaluation
  • IPA
  • Grounded theory

Data coding comes first in any qualitative data analysis, which is followed by one or more analytical methods.

  • Descriptive statistics like means, medians, and modes are included in standard data analysis techniques in quantitative research.
  • Inferential statistics, including correlation, regression, and structural equation modelling.

Once more, your research’s overarching aims and objectives, as well as practical considerations and the resources that are available, will influence the technique of data collection you select.

How do I choose the best research methodology?

To do research successfully, careful preparation and execution are required. Your research goals and objectives will significantly impact the research process, as you have presumably realized by this point. Therefore, before making technique decisions, sit back and consider the overall context of your research as a beginning point for constructing your research approach. For example, suppose your research is exploratory or confirmatory. That is the first thing you need to determine. If your primary goals and objectives are exploratory, your review will generally be subjective. As a result, you could want to think about subjective information gathering techniques for your investigation methods, such as meetings and subjective substance examination.

On the other hand, if the aims and objectives of your research are corroborated ‚ÄĒthat is, they attempt to measure or test something‚ÄĒthen your review will likely be quantitative. So you can think about using quantitative information gathering techniques like overviews and examinations like factual investigation.

In subsequent posts, we’ll cover various topics, including how to organize your examination and choose your methodology. The most crucial thing to keep in mind right now is that you should always start with the reasons and goals of your exam. The basis for all procedural decisions will be that.

Chapter 2: Qualitative vs. Quantitative Research

Qualitative vs. Quantitative Research  

Now is the time to choose between a qualitative and a quantitative research technique. And most likely, you want to select the option that gives you the slightest sense of dread. Because they detest engaging with people and handling “soft” issues and find numbers and algorithms to be far more comfortable, engineers may be drawn to quantitative methods. On the other hand, anthropologists are likely more enthusiastic about qualitative methods since they have opposite anxieties.

But using “fear” as a justification for your investigation is not a wise course of action. Your research goals and objectives should guide your approach rather than your personal preferences. Additionally, it happens frequently that the method you feared‚ÄĒqualitative or quantitative‚ÄĒis not that significant. The software dramatically decreases the complexity of quantitative and qualitative data processing, and research methodologies can typically be mastered much more quickly than you may imagine. On the other hand, picking the incorrect strategy and attempting to squeeze a square peg into a round hole would only lead to even greater suffering. Data collection procedures for qualitative and quantitative studies are very varied since they use different data types.

Qualitative Research

Qualitative and quantitative research use distinct data collection methods because they use different data types. Obtaining and analyzing non-numerical data is one of the techniques used in qualitative research. For example, it’s warm in the bathtub.

Let’s explore that further. What exactly does the phrase mean? Is it helpful, too?

Well, that depends is the response. If you’re looking for the bath’s exact temperature, you’re out of luck. But if you put on your qualitative hat and try to understand how someone feels about the temperature of the bathwater, that line can tell you a lot. For example, many husbands and wives have never shared a bath due to their deeply held, relationship-destroying beliefs about water temperature. Additionally, analyses of the inevitable discussions and disagreements surrounding water temperature would be more at home in quantitative research due to variances in how people perceive water temperature. However, they would be more at home in qualitative research. Qualitative research enables you to comprehend people’s opinions and experiences¬†by methodically coding and evaluating the data.

Pardon the pun can examine those heated arguments using qualitative research. Ideally, outside the restroom, from interviews to focus groups on directing observation. How the argument develops or the emotional language used during the discussion may interest you as the researcher. For example, you might be more interested in the body language of someone who has been repeatedly dragged into (what they perceive to be) scalding hot water during what was supposed to be a romantic evening than you are in the actual words.

Qualitative research can help us comprehend all of these softer characteristics. Qualitative research may be rich and thorough in this approach, frequently used as a foundation for developing ideas and spotting trends. As contrast to confirmatory research, which aims to test a hypothesis, it is effective for exploratory research, which aims to discover more about people’s viewpoints. Qualitative research is used to better comprehend human viewpoint, worldview, and how we communicate our experiences.¬†It involves investigating and comprehending a big question, frequently with minimal assumptions about what we might discover.

Quantitative Research

But for quantitative studies, different data collection methods are required. These procedures include collecting numerical data to explore the causal relationships between numerous components. For instance, the temperature of the bathwater is 45 ¬įC.

What does this mean, exactly? What is the use of this?

Someone, I am not married to informed me that he frequently takes cold showers. This seems absurd because I’m frightened of anything that isn’t body temperature or above. But this begs the question: what temperature makes the ideal bath? Or, at the very least, what is the average temperature of baths? Assuming they are bathing in water, that is ideal for them. You must now put your quantitative hat on to respond to this question. We could determine each person’s average bathwater temperature if we asked 100 people to record the temperature over a week. Let’s say Jane’s temperature is typically about 46.3¬įC. Billy’s temperature is typically 42 degrees. The unnatural chill of 30¬įC on a typical workday may be appealing to a few people. There will be some of those attempting to reach the 48¬įC that is reportedly the current legal maximum in England, so there you have it as a useless fact.

There are many different approaches to analyzing this data using a quantitative approach. For instance, we may examine these data to determine the average temperature or see how widely these temperatures range. We could check to determine if the ideal water temperature varies significantly between the sexes or if there is a connection between the ideal water temperature and age. We could plot this data on vivid, colorful graphs using fancy terms like significant, correlation, and eigenvalues. There are plenty of chances to nerd out. In this sense, it is customary in quantitative research to go into your study with some anticipation or comprehension of the results, typically in the form of a hypothesis you want to test. Keep this in mind: Men are said to enjoy baths in cooler water than women. Then, using statistical analysis, this hypothesis can be verified. The data might support the hypothesis or show some subtleties regarding people’s preferences. Men, for instance, might prefer a hotter bath on particular days. As you can see, each qualitative and quantitative research method serves a distinct purpose. Simply put, they are various tools used for various tasks.

What are you precisely wanting to understand about your topic is perhaps the most crucial factor to take into account? Do you intend to test any specific theories or predictions? Do you wish to ascertain the relationships between the ideas or elements of your subject? Do you wish to compare the differences in the relevant variables between particular groups of people? Such objectives can be addressed through a quantitative investigation. On the other hand, a quantitative method will generally work best if you need to test an existing theory or wish to measure and describe something statistically. A theory or even merely a hypothesis that was developed through qualitative research, for instance, could need to be put to a quantitative test.

This indicates that your research approach should be decided upon in light of your larger study goals, objectives, and research questions. Qualitative research enables you to ask open-ended questions and, in some cases, let subjects and participants speak for themselves if your research is exploratory. As a result, you are unsure of what conclusions may be found. Quantitative inquiries won’t, on the other hand. They frequently provide pre-categorized options or let you enter a numerical response. A quantitative approach will be required for anything that calls for measurement utilizing a scale, device, or thermometer.

Let’s say you want to find out people’s preferred bath temperature. Here are three possible approaches to accomplishing this via a survey or questionnaire:

  1. How do you feel about your partner’s preferred bath temperature? Qualitative. This open-ended question gives the reply plenty of room to rant effectively.
  2. What temperature do you prefer for a bath? Most individuals won’t know the answer to this one or won’t have a thermometer, but it is a quantitative question with a clear numerical solution.
  3. . Among the following comments on the temperature of your bathwater, please choose the one you find most pertinent: It’s too warm. It fits perfectly. It is too chilly. Quantitative in that you may compare the results by adding the total number of respondents for each response option.

The responses can be utilized in various ways, but qualitative responses require a lot of thought. Therefore, they are repackaged in a way that attempts not to lose too much significance, while quantitative responses can be readily summarised by counting or calculating, classifying, and visualizing.

Qualitative vs Quantitative Research:

The volume of data gathered distinguishes qualitative from quantitative research the most. The qualitative method is frequently used in research to create hypotheses or develop concepts for more study. Once a hypothesis or an idea has been created, the researcher can test the hypothesis or concept and gather statistical data to support it using the quantitative technique. Finding the causes of a particular behaviour or event or creating research hypotheses are two common uses of the qualitative approach.

In short, collecting data for qualitative research requires fewer samples, but the data are more prosperous and in-depth. However, in quantitative research, generalisations about a population must be made using data from a large sample size. For example, we would require data from hundreds of individuals to draw a general conclusion from our examination of bathwater. We would require at least a few dozen to detect a probable pattern. We would likely turn to a more scalable technique like an online poll to obtain relatively simple data.

Data collecting for quantitative research includes huge sample sizes compared to qualitative research but relatively simple data.

Both research methodologies employ analyses that let you define, describe, and contrast the subjects of your interest. Quantitative research accomplishes this by transforming your data into numbers or graphs, whereas qualitative research does so by analysing words, texts, and explanations.

Each uses one of the many potential analyses available. Examples of qualitative analysis are the sad story of a love lost due to insurmountable water tolerance issues or the actual content, such as the phrases of blame, heat, and aggravation used in an interview. Quantitative analysis might entail straightforward average calculations or more complex analysis that examines the connections between two or more factors, such as personality type and the propensity to commit a crime involving hot water. I won’t bore you here with the minutiae of the various analysis options because we cover them in other blog postings.

The advantages and disadvantages of both qualitative and quantitative research methods

There are many benefits to performing qualitative research. One benefit is that it enables outcomes that are often unexpected but richer and more informative. We frequently need this when we wish to explore a study question further. Qualitative research is the best method to use when attempting to understand people’s thoughts and emotions. Research is equally crucial when exploring and discovering something new when you are unsure of precisely what you are looking for. Finally, when seeking to construct theories, you’ll use qualitative research because it provides more substance for our understanding of the world.

Qualitative research has another benefit over quantitative research in that it is typically more adaptive and versatile. This is so because qualitative research frequently places a greater emphasis on the process of data gathering than on the findings. This means that, if necessary, qualitative researchers can alter their methodology midway through a study. This flexibility can be helpful, mainly when the research topic is complex or delicate.

Finally, compared to quantitative research, qualitative research is frequently thought to be more “genuine” or “real.” This is so because individual participant experiences, as opposed to generalised data, are typically more the emphasis of qualitative research. This means that a qualitative study might offer a more thorough and complex knowledge of a study subject.

In qualitative research, observational techniques are used to obtain information about individuals, their behaviours, and the communities in which they live. Qualitative research aims to deliver a detailed, in-depth explanation of the research issue.

Qualitative research is frequently employed to explain previously observed occurrences with findings that fall outside the purview of quantitative study. Qualitative research can also be used to describe what is happening now or has already been noticed in the past. For instance, doing a cold-bath-induced anger interview with a subject can help flesh out some of the minutes and frequently overlooked nuances of a research topic. We might discover, for instance, that some respondents associate taking a bath with memories from their youth when hot water was a luxury that was out of reach. A quantitative technique would never be able to detect something like this.

The qualitative research has a variety of valuable features as well. A smaller sample size allows the researcher to be more selective in their approach. The affordability of this is related. Qualitative research frequently calls for less sophisticated and expensive data collection and analysis technology, unless you have to shell out a lot of money to watch the Hadza hunting techniques in Tanzania.

Numerous drawbacks exist with qualitative research. The findings might not be universally applicable due to the tiny sample size. This makes it challenging to do a similar study again. What if, for instance, the individuals you initially spoke with also happened to be particularly enthusiastic about bathwater? What if one of your eight interviews was with someone so incensed by receiving a cold bath in the past that she wrote an entire blog post using this absurd and obscure example? The sample size is simply one limitation of this study, though. The interpretation of the data can be significantly impacted by a researcher’s bias in data analysis. Research can be constrained in this way. Consider the possibility that they had preconceived notions about the interview subject and, as a result, forgot to bring up a crucial or pivotal topic.

Furthermore, a further restriction is the lack of experience of the researcher. A skill that develops with time is interviewing and observation. The findings of a qualitative study may be challenging to duplicate, and the theories or frameworks employed may be highly problematic if the qualitative researcher is unaware of their own biases and limitations throughout the data collecting and analysis phases. Collecting and analysing data from a single source for qualitative research takes a lot of time. Sample sizes are frequently somewhat modest because of this. The hour-long interview? Most likely, you’ll need to hear it twice or three times. And read it six more times from the recorded transcript. Then, along with the remainder of the interviews, reformulate and categorise the remaining portions of the interview.

Let’s now discuss quantitative tools

Using straightforward quantitative tools, it is possible to visibly and officially support or challenge ideas or hypotheses. For example, how many women are tired of taking ice-cold showers, do you want to know? Boom! The proportion is shown below the pie chart. The pie chart also includes a picture of an actual pie to appease the voracious, furious mob of cold-water haters.

Quantitative research is valued for its objectivity and integrity. It can be used to maintain or enforce societal consensus and governmental policies. If the analytical strategy is unsuccessful, the remaining pie can be directed at politicians who try to establish maximum bath water temperature restrictions. It is straightforward, widely regarded, and essential. Aside from helping you comprehend WHAT is happening in your data, large sample sizes, significance tests, and half-eaten pies are other elements that can also assist you in determining whether your conclusions will hold up to further examination. A fundamental premise of the scientific method is this.

Quite fast, a quantitative investigation can be finished. For example, a subject can respond to a quantitative survey more quickly than a qualitative interview. Hence the process of acquiring data is often quicker. A further benefit of the data analysis method is its usual speed. If you’re feeling very sophisticated, you could create and automate your analyses as the data come in! It would be best if you didn’t worry about including a lengthy analysis session in your research time.

Last but not least, anonymity is a critical ethical consideration that can occasionally, but not always, be guaranteed in quantitative research. Instead of an interview, a survey could appear less intrusive, which might encourage participants to be more sincere. Of course, this isn’t always the case. In surveys with insufficient sample numbers, such as those performed within small departments, respondents may still be concerned about their anonymity.

However, there are quantitative drawbacks…

A quantitative study can oversimplify or be somewhat reductive of a situation. Since quantitative analysis focuses on averages and comprehensive correlations between variables, outliers are typically ignored. That one person takes an ice bath weekly for no apparent reason. Quantitative research may not reveal everything.

Large sample size is necessary for it to be meaningfully employed. It would help if you had a substantial dataset to claim that your data and results are noteworthy about the population you are studying. In particular, for unpaid or self-funded research like a master’s thesis or research, large sample sizes are frequently difficult to achieve. Actual sample sizes are required to get statistical power and results with statistical significance.

Quantitative techniques call for specific experience and knowledge, occasionally more knowledge than the bulk of those who use them. To see potential flaws in your research design and others, it’s equally important to read and comprehend what others have done. If you have a foundation in statistics, this won’t be a problem, but most students don’t have this luxury.

Finally, quantitative researchers are less likely to admit or examine their personal biases in their work because they believe that objectivity must be true given the numbers. Because of the assumption of impartiality, researchers typically overlook the importance of choosing the proper sample, sorts of questions to ask, and analysis method.

Mixed methods: a happy medium?

Some of the more interesting studies I’ve seen used qualitative and quantitative research techniques. Quantitative research gives the researcher the ability to provide a comprehensive picture of the issue or topic, whereas qualitative research provides more profound insights. Combining the best features of both worlds is the aim of mixed-methods research.

In your research survey, open-ended questions can help you accomplish this practically. This can be achieved by having a discrete qualitative segment with several interviews or a preliminary survey from which you can choose sure interviewers. In addition, it may require observations, some of which you would anticipate seeing and might quickly note, categorise, and measure, while others are novel and require a more thorough justification.

A word of caution: Using mixed approaches should only be made after carefully considering the goals, objectives, and research questions. This is comparable to deciding whether to conduct qualitative or quantitative research. Avoid using a mixed-methods approach if you are unsure whether to employ quantitative or qualitative research. It is challenging to approach mixed methods research; continue with caution!

A Review of Quantitative vs Qualitative Research,

So, just to summarise all we discovered regarding the famous qual vs quant controversy in one chapter:

  1. Quantitative research is better suited to more affirmative research, such as hypothesis testing. In contrast, qualitative research is better suited to exploratory research, such as developing a theory or hypothesis.
  2. Qualitative research uses words, phrases, descriptions, or ideas as data. The sample size is modest because it takes a lot of time.
  3. Quantitative research employs numerical data that can be represented visually as graphs. Therefore, large sample sizes are necessary for meaningful results.
  4. Rather than being influenced by your worries or preconceived notions, your methodological choice should be more influenced by the type of question you pose.
  5. Hybrid approaches can be an excellent middle ground, but they should only be employed on purpose.
  6. Bathwater temperature is a controversial and woefully under-researched subject.

Chapter 3: How To Choose Your Research Methodology

Undoubtedly, this is one of the questions Skylink Research receives most frequently. It makes sense; with so many options for research design, it’s easy to feel intimidated. However, proper planning and execution are required to do research successfully.

Overview: Selecting Your Approach

Although there are many reasons and explanations why a research project is successful, selecting a suitable research methodology is one of the most complex and challenging decisions. To support your work and data gathering strategies, you must develop a research methodology because the approaches you use will depend on the results of your study. If you select the appropriate research strategy, you may collect the required data and meet the study’s objectives.

  1. Being aware of your possibilities, such as research using mixed methodologies, qualitative research, and quantitative research
  2. Picking a research strategy
  3. research area rules and the nature of the study
  4. Practicalities
  5. Understanding the options

A broad understanding of the three main categories of research-mixed-methods, qualitative, and quantitative-is important before diving into the issue of selecting a research approach. These choices all follow various strategies.

Data that are not dependent on statistics are utilised in qualitative research. To put it another way, qualitative research places a stronger focus on words, descriptions, concepts, or ideas, whereas quantitative research relies on data and figures. To analyse and characterise problems, qualitative research looks at the more subjective aspects of things. Comparatively, complex numbers are the main focus of quantitative research, which employs them to analyse the fluctuations in the variables and how they are related.

Notably, qualitative research methods are usually used to investigate and understand the intricacy of a topic in order to present a full picture. On the other hand, many people use quantitative methods to verify or evaluate their assumptions. That is to say, they serve completely distinct purposes. On the variants, you may find more information here. Some key contrasts between qualitative and quantitative research are shown in the table below.

  • Qualitative Research

A sort of study known as qualitative research employs data that is not numerical. In order to comprehend people’s viewpoints, experiences, and beliefs, this kind of study is used. Qualitative research is often used in the social sciences, but it can be used in other disciplines.

Numerous varieties of qualitative research exist, but some standard methods include focus groups, interviews, and observations. In addition, qualitative research is often used to explore a new topic or understand a complex phenomenon.

Qualitative research is conducted using various methods, and the choice of method depends on the research question. Focus groups, interviews, and observations are a few typical qualitative research techniques.

Focus groups are intimate gatherings when a topic is brought forward for discussion. The discussion is usually led by a researcher, who will ask questions and probe for deeper understanding.

Interviews are private discussions between a participant and a researcher. The participant replies to questions posed by the researcher. The interviews can be structured, with predetermined questions, or unstructured, with the conversation flowing more freely.

Observations involve the researcher watching and taking note of what is happening. This can be done in a natural

  • Quantitative Research

Quantitative research is a research methodology that uses numerical data to answer a research question. To do this, quantitative researchers collect data through surveys, experiments, and other data-gathering methods. Once they have collected this data, they use statistical analysis to conclude their research question.

There are many advantages to using quantitative research. The first benefit is that it enables quick data collection for researchers. This is especially useful when researching a population that is difficult to access, such as a rare disease. Second, quantitative research is highly replicable, meaning that other researchers can use the same methods to collect and analyse data to see if they get the same results. This makes it easier to build on the previous research and verify findings.

However, there are also some disadvantages to using quantitative research. First, it can be challenging to collect accurate data, especially if the research question is complex. Second, statistical analysis can be challenging to interpret, and it is often easy to make mistakes that can lead to inaccurate conclusions. Finally, quantitative research does not always give researchers a deep understanding of the people they are studying. For example, surveys can only ask people about their opinions and experiences rather than observing them directly.

  • A mixed-methods Research

A mixed-methods research is an inquiry approach that uses quantitative and qualitative data to answer research questions. In many cases, mixed methods research is used to study social phenomena and understand human behaviour.

A mixed-methods research can study various topics, including social attitudes, human behaviour, and social interactions. For example, a researcher might use mixed methods to study how people interact with one another in a social setting. In this case, the researcher would use both quantitative and qualitative data to understand the people’s behaviour in the social setting.

A mixed-methods research can also be used to study human emotions and attitudes. For example, a researcher might use mixed methods to study how people feel about a particular issue. In this case, the researcher would use both quantitative and qualitative data to understand the emotions and attitudes of the people.

In other words, they are not incompatible despite the fundamental differences between qualitative and quantitative procedures and the ideas that support them. It’s not a battle between qualitative and quantitative approaches. Instead, they can be combined to produce an excellent piece of study. Since it is obvious that this is easier said than done, we often advise beginning researchers to adhere to a single technique unless their subject truly justifies a mixed-methods approach. The primary lesson here is that each methodological methodology has a different goal: to research and comprehend problems qualitatively, test and measure statistically, or accomplish both. This is why we started by looking at the three choices. They do more than only act as alternatives to other tools for the same job.

After everything has been clarified, let’s examine how to select the ideal study plan.

How to choose a research methodology

The optimal research methodology for a given project will rely on various variables, including the nature of the research topic, the data at hand, the resources and time at hand, and the researcher’s preferences and skills. There is no one size fits all answer to this question. When selecting a research methodology, there are, however, some general rules that can be followed.

Factor #1: The type of study you’re undertaking

One of the first considerations should be the nature of the research question. Some questions can be answered using existing data, while others require collecting new data. Some questions may be best suited to qualitative methods, while others will be more appropriate for quantitative methods. For example, if you want to study the effects of a new teaching method on student achievement, you would use an experimental research design. This would involve randomly assigning students to either the new or the traditional teaching method and then measuring their achievement levels. This is the best way to ensure that any differences in achievement levels are due to the teaching method and no other factors.

And if, on the other hand, you want to study how different types of students respond to different types of teaching methods, you would use a qualitative research design. This would involve observing and interviewing students and teachers to get a detailed understanding of the experience. This is the best way to understand the complex relationships between students, teachers, and the learning environment.

There is no single correct research methodology. The best methodology is the one that is best suited to your particular research question. The data available will also play a role in choosing a research methodology. If data already exists, it may be possible to use secondary data analysis. If primary data gathering techniques are required, they include surveys, interviews, and observation.

Important factors will also include the time and resources available. It may take longer to conduct some research methods, and some require more resources than others. It will also be essential to consider the researcher’s preferences and abilities; specific approaches can be more comfortable or straightforward to use than others. The first and most important consideration when deciding the methodological methodology to use for your research project should thus be the nature of your research’s goals, objectives, and research questions.

Choose whether your study is predominantly exploratory, mostly confirmatory, or a blend of the two. These three requirements and your methodology must be highly consistent. You will be attempting to fit a square peg into a round hole if they are not lined up. In other words, your research will be a disorganised mess because you’ll be utilising the incorrect tool for the job.

 Suppose you have a strict word count requirement, and your study involves both exploratory and confirmatory methods. In that case, you may need to think about narrowing the scope and concentrating on one or the other. A single methodology effectively has a higher possibility of receiving high scores than a hybrid approach. Therefore, unless solid foundational logic exists, avoid attempting to be a hero.

Factor #2: Precedence 

Examining the methods used by other researchers in the area and studies with goals and objectives that are similar to your own is a vital step in choosing the best methodology for your study. It is not uncommon for studies conducted within a profession to use the same methodological methodology or procedures. This is not to say that you should merely follow the crowd, but you should at least think about these ideas and determine whether they apply to your situation.

You may frequently improve on the data gathering strategies created by other, more seasoned researchers if you analyse the research methodology utilised in comparable studies in your field. For instance, if you’re doing a quantitative study, you can frequently come across tried-and-true survey scales with high Cornbrash’s alphas. The original authors are typically included in the appendices of journal papers, so you may avoid even having to get in touch with them. Utilising these can save you a tonne of time and ensure that your research is based on measurement techniques with a long history.

In other words, your research goals, objectives, and questions must all be consistent with your approach. Avoid following other research methodological norms just because they are widely used. Instead, adopt only what is pertinent to your research.

There are several disciplinary norms that researchers need to take into account when planning and conducting their research. These norms include:

  1. Adhering to ethical principles ‚Äď researchers must ensure that their research is conducted ethically and under the relevant ethical principles and guidelines
  2. Following research protocols ‚Äď researchers need to follow the agreed-upon research protocols to ensure the validity and reliability of their research
  3. Maintaining confidentiality ‚Äď Do researchers need to maintain the confidentiality of all information and data collected during their research?
  4. Complying with legal requirements ‚Äď Researchers must ensure that their research complies with all relevant legal requirements
  5. Adhering to institutional policies ‚Äď Researchers must adhere to their institution’s policies concerning research conduct and ethics

Factor #3: Practicalities

When choosing a research strategy, there will inevitably be a trade-off between accomplishing what is realistic given your constraints and what is theoretically best or the most rigorous scientific study design. There are always trade-offs involved in research, just like in anything else. A research question can be investigated using a variety of different research approaches. The type of research issue, the resources available, and the tastes of the researcher all frequently influence the choice of research methodology.

Practicalities such as time and money can also play a role in determining the most appropriate research methodology. For example, a researcher interested in investigating a question that requires a large amount of data may not have the time or resources to collect all of the data themselves. In this case, they may need to use a secondary data source.

Secondary data sources are data that have already been collected by someone else. For example, data from the census, surveys, or administrative records. Using a secondary data source can be less time-consuming and expensive than collecting data from scratch. However, it is essential to note that secondary data sources may not be appropriate for all research questions. In some cases, it may be necessary to collect primary data.

Primary data is data that the researcher collects. This can be done through interviews, focus groups, or questionnaires. Collecting primary data can be more time-consuming and expensive than secondary data sources, but it can also be more tailored.

The instruments that researchers employ to gather data are known as research methodologies. There are several study methodologies, each having advantages and disadvantages. The research method you choose will depend on your research question, the available resources, and the type of data you need.

Research techniques frequently include questionnaires, interviews, focus groups, observations, and experiments. A form of research technique called a survey includes posing questions to a sizable population. An interview is a form of research technique that involves questioning a small number of people. Focus groups are a research technique wherein a few individuals are questioned in a less formal setting. A research technique called observations involves seeing individuals or other objects in their natural surroundings. Finally, a research strategy known as an experiment involves changing one variable to observe how it affects another variable.

There are many other research methods, and the type of research method you choose will depend on your specific research question and the available resources. If you are unsure which research method to use, you can consult with a research methodologist or statistician to help you choose the best method for your needs.

Several practical considerations must be considered when designing a research methodology. The researcher must first think about the research’s goal and the most effective ways to accomplish it. For example, suppose the research purpose is to examine a new product’s impact on consumer behaviour. In that case, a suitable methodology might be to survey consumers who have used the product.

Another practical consideration is the availability of resources. The researcher needs to consider the available data and how best to collect it. For example, if the researcher wants to collect data on consumer behaviour, they will need access to a sample of consumers. This might be achieved through various methods, such as conducting a survey or collecting data from an existing database.

The researcher must also think about the research’s timeline. This will impact the choice of methodology. For example, a survey might be the most appropriate methodology if the research needs to be conducted quickly.

Review: Picking the best methodology

We considered three main decisive elements when choosing a methodology for your research.

  1. The type of research question you are asking
  • Exploratory
  • Confirmatory
  • Combination
  1. The type of data you are collecting
  1. The resources you have available
  • Data access
  • Time
  • Money
  • Hardware and software
  • Your knowledge and skillset

The type of research question you are asking is the most crucial deciding factor in choosing a methodology. If you are asking a question requiring a quantitative answer, you will need to use a quantitative methodology. If you are asking a question requiring a qualitative answer, you will need to use a qualitative methodology. The type of data you are collecting is also an important deciding factor. If you are collecting quantitative data, you will need to use a quantitative methodology. If you are collecting qualitative data, you will need to use a qualitative methodology. The resources you have available are also an important deciding factor. If you have access to a large amount of data and the resources to analyse that data, then you will be able to use a more complex methodology. Conversely, you must use a more straightforward methodology if you have limited resources.

Please feel free to ask any questions on our contact page. Our helpful Skylink Research representatives will answer all your questions as they regard your methodology chapter help.

Chapter4: Understanding Saunders Research Onion

Learn about the decisions you’ll need to make when choosing a study design, from the research philosophy to the particular data analysis methods.

Saunders’ research onion

The phrase “peeling the onion” is often used to describe the process of slowly revealing the truth about something, layer by layer. For example, imagine that you are trying to solve a mystery. You might start by looking at the big picture, then zoom in and look at the details, then zoom out again to see the big picture, and so on. Slowly uncovering the truth is like peeling an onion, layer by layer.

What is Saunders’ 2007 research onion?

The 2007 research onion is a model developed by Dr John W. Creswell and Dr Steve D. Saunders that helps researchers design their research projects. The onion comprises six layers, starting with the innermost layer of philosophical assumptions, moving outward through methodology, data collection, data analysis, and finally, the conclusion. This model helps help researchers determine what type of research design is most appropriate for their project and what methods and data will be most helpful in answering their research question.

The first layer of the onion is philosophical assumptions. This is where researchers will need to identify the assumptions that they are making about the nature of reality and knowledge. These assumptions will guide the rest of the research project, so it is essential to be clear about them from the outset. The second layer is methodology. This is where researchers will need to decide what type of research design is most appropriate for their project. This will involve choosing between qualitative and quantitative methods, as well as between experimental and non-experimental designs.

The third layer is data collection. This is where researchers must decide what type of data they will collect and how they will collect it. This will involve choosing between primary and secondary data and qualitative and quantitative data. The fourth layer is data analysis. This is where researchers will need to decide how they will analyse the collected data. This will involve choosing between qualitative and quantitative data analysis methods. Finally, the fifth layer is the conclusion. This is where researchers will need to draw conclusions from their data and determine their research implications for theory and practice.

The layers of Saunders’ research onion

Saunders’ 2007 research Onion is a model that helps researchers plan and structure their research. It is based on the idea that six elements need to be considered when planning research:

  • The research questions
  • The research objectives
  • The research strategy
  • The data collection methods
  • The data analysis methods
  • The research findings.

Each of these elements is represented by a layer of the onion, with the research question at the centre and the other elements progressively surrounding it. From the early planning stage until the drafting of the final results, the model may be employed at various points during the research process. It is beneficial for helping researchers to think about how their different choices will impact their research overall direction and outcome.

One of the main advantages of the model is that it forces researchers to consider all aspects of their research before starting, which can save a lot of time and effort later on. It can also help identify potential problems early on, so they can be addressed before they cause too much damage. While the model is not perfect and will not work for every research project, it is a valuable tool that can help make the research process simpler and more effective.

Onion Layer 1: Research Philosophy

Philosophy is the topmost layer of Saunders’ research onion. Philosophy is information that has previously been gathered and published, usually in some form. Sources for this information include books, journal papers, and online databases. This might be founded on a specific theoretical viewpoint, like an ontological or epistemological one. The nature of reality and what people are genuinely capable of knowing and understanding can be described as ontology, or the “what” and “how” of knowledge. Exists a single objective reality, for example, or is reality relative to each person? Think about how The Matrix depicts virtual reality.

Contrarily, epistemology is concerned with how we acquire knowledge, how to define reality and the limits of our knowledge, and how to study and understand things. This is obviously oversimplified, but it’s a great place to start; ontology and epistemology will be handled later.

Let’s analyse three key research philosophies that are founded on diverse ontological and epistemological foundations after cutting through the fluff:

  • Positivism
  • Constructionism
  • Pragmatism

Although these are the only research philosophies, they are the most common and provide a useful starting point for understanding the variety of concepts.

¬†Positivism –¬†Positivism is a philosophical and methodological approach that emphasises using scientific methods to study social phenomena. Positivists believe that social phenomena can be studied scientifically and that knowledge about them can be acquired through applying the scientific method.

Positivism has its roots in the work of the French philosopher Augusta Comte, who argued that all knowledge is acquired through the scientific method and that all social phenomena can be studied scientifically. Comte’s positivism was later elaborated on and refined by other thinkers, including the German sociologist Max Weber

The growth of social science has been significantly influenced by positivism. It has helped shape the way social scientists think about the nature of social phenomena and the methods that can be used to study them.

Some social scientists have criticised positivism because it is too deterministic and fails to consider the role of human agency in shaping social phenomena. Nonetheless, positivism remains a robust and influential approach in the social sciences.

Constructionism –¬†Constructionism is a research philosophy that holds that the meaning of a phenomenon is best understood through the interpretation of the experiences and perspectives of those affected by it. In other words, Constructionism is based on the idea that reality is socially constructed and that there is no single objective truth.

One example of Constructionism in action is a study that seeks to understand how people experience a particular phenomenon, such as poverty. For example, researchers using a Constructionism approach would interview people living in poverty and ask them about their experiences. To better understand how poverty impacts people’s daily lives, they would also consult other sources, such as diaries.

Another example of interpretivism is a study examining how people interpret a law or policy. For instance, a researcher might interview people about their understanding of a new law that requires all businesses to provide health insurance to their employees. The researcher would then interpret the data to understand how people make sense of the law and how it affects their lives.

Pragmatism –¬†Pragmatism is a philosophical tradition that emphasises the practical application of ideas over theoretical or abstract speculation. Pragmatists believe that knowledge is always provisional and that truth is relative. They contend that the only way to gain accurate knowledge about something is to test it in the real world and see how it works.

Pragmatic philosophy originated in the work of American philosopher Charles Sanders Peirce (1839-1914). Peirce developed the idea of pragmatism to understand how we know things and how we can acquire new knowledge. He argued that the meaning of a concept is not fixed or static but is constantly evolving and changing as we use it and test it in different ways.

Pragmatism has influenced several fields, including politics, sociology, economics, and education. In each of these areas, pragmatists have argued that we must take a practical, experimental approach to problem-solving.

For example, in education, pragmatists have advocated for an approach to learning that emphasises active, hands-on experience over rote memorisation. In politics, pragmatists have argued that incremental reform is the best way to achieve progress.

In conclusion, research philosophy serves as the foundation for all research endeavours and contains the ontological and epistemological suppositions of the researcher. Therefore, considering which philosophy to embrace in light of the nature of your research is the first step in constructing your research approach.

Onion Layer 2: Research Approach

When conducting research, it is essential to consider the different approaches that can be taken. Each approach has its strengths and weaknesses, so choosing the most appropriate approach for the question being asked is essential. For example, if a researcher wants to comprehend how individuals make decisions, they might use a qualitative approach such as interviews or focus groups. On the other hand, if a researcher is interested in understanding how people’s attitudes towards a particular issue change over time, they might use a quantitative approach such as a survey.

There are many different research approaches, but some of the most common are described below.

Qualitative research approaches focus on understanding phenomena from the participants’ perspective. This type of research is often used to explore new or complex topics. In addition, qualitative approaches are often used to generate hypotheses or to understand the experiences and perspectives of participants. Focus groups, participant observation, and interviews are typical qualitative research methods.

Quantitative research approaches are those that focus on measuring and analysing numerical data. This type of research is often used to test hypotheses or examine relationships between variables. In addition, quantitative approaches are often used to collect data that can be analysed using statistical methods. Some common quantitative research approaches include surveys, experiments, and data.

In conclusion, deductive and inductive research methodologies are used. You need to evaluate the kind of research you hope to do to choose the best approach for your study. Consider whether your research will add to an existing body of knowledge or whether you’ll be looking into a topic that may not necessarily have a foundation in earlier studies. The first suggests a deductive strategy, and the second is an inductive strategy.

 Onion Layer 3: Research Strategy

We’ve mainly examined abstract and intangible characteristics of the onion up to this point. It’s time to expand that onion by one more layer and move on to research strategy, which is more useful. Depending on the goals of the investigation, a variety of methods are described in this area of the research paper. Let’s look at a few ways you can use it.

  • Experimental studies
  • Action study
  • Case study investigation
  • Based hypothesis
  • Ethnography
  • Archival analysis

Experimental studies –¬†To assess the connection between factors, exploratory examination incorporates transforming one variable, the free factor, to check whether another variable, the reliant variable, changes. Trial and error are utilised to affirm, deny, or support a review hypothesis. This study technique sticks to the essentials of the logical cycle and is done in a controlled setting, like a research centre. The exploratory examination is rational since it tries to test laid out hypotheses instead of fostering new ones. Expecting that data must be investigated unbiasedly and aside from external components like climate or culture, the exploratory review follows the positivist examination reasoning.

A trial study assesses the impacts of the specific brand on a regular eating regimen on the off chance that you hypothesised that a specific brand of canine food could expand a canine’s protein levels. To put it another way, you could confirm your hypothesis.

For this situation, you would have two gatherings: the benchmark group, which comprises canines whose diets had not been adjusted, and the trial treatment bunch, which comprises little guys who took care of the brand you expected to study. The protein levels in the two gatherings would then be contrasted to affirm your speculation.

Action research –¬†Activity research is the accompanying: Action research consolidates advancing by preparing for itself and activity, which is the least demanding method for characterising it. Unlike controlled settings like a lab, activity research is done in genuine circumstances like a school, clinic, work environment, and so on. Activity research helps with teaching scholastics about issues or blemishes in certifiable experiences. Activity research, otherwise called participatory activity exploration, or PAR, centres vigorously around the members and the people engaged with the subject being inspected.

Local area intercession for treatment, cultivating, schooling, or some other design is an outline of PAR. The people group, or the members, helps the scientist try their hypothesis. The people group then talked about the discoveries to decide how to work on the mediation. Until the intercession impeccably serves the local area, the system is rehashed. As such, an issue is furnished with a proper arrangement delivered through the collaboration between the specialist and local area member input.

This examination is ordinarily utilised in the sociologies, especially in callings where individuals need to get better at their identity and what they do. However, activity research is often utilised in subjective examination and rarely used in quantitative exploration. This is because the activity research utilises language and connections instead of insights and figures, as shown in the models above.

Case study research –¬†A contextual analysis is exhaustive, inside and out, assessing a solitary subject, like an individual, a group, an association, an event, peculiarity, or an issue. In this exploration, the subject is inspected to understand issues in a helpful circumstance. Here, the objective is to acquire exhaustive information on the review’s setting instead of fundamentally summing up the discoveries.

Because of the significance of considering the social climate and culture while conducting contextual analysis research, this kind of examination is frequently subjective and will generally be inductive. Furthermore, a contextual investigation research, for the most part, utilises an interpretive way of thinking because the scientist’s suppositions and understanding are significant. For example, research on the political assessments of a specific gathering of people should consider the country’s present political environment and whatever other conditions that would impact members to have a specific assessment.

Grounded theory –¬†The grounded hypothesis comes straightaway. Allow the proof to represent themselves while fostering a grounded hypothesis. In other words, while utilising a grounded hypothesis, you permit current realities to direct the production of a new plastic hypothesis, model, or system. The speculation you assemble depends on the information consistent with its name. In this way, the ground hypothesis is beneficial for studying subjects that are either neglected or understudied.

Even though it can likewise utilise quantitative information and an inductive strategy, a grounded hypothesis research is fundamentally subjective. This kind of exploration regularly begins with contrasting various arrangements of information with recognised examples, and ends are accepted from the concentrate overall without attempting to squeeze the outcomes into a current hypothesis or system.

For example, if you somehow managed to concentrate on the folklore of an unfamiliar culture utilising relics, you wouldn’t begin your examination with any thoughts or speculations; all things being equal, you would fabricate them as you look into the subject.

Ethnography –¬†In ethnography, individuals are seen in their traditional settings while significance is surmised from their social connections. Ethnography aims to record the members’ abstract view of the world and see it according to their viewpoint.

For example, you could use ethnography to look at cooperation and grasp the members’ emotional encounters on the off chance you were keen on exploring collaborations on a psychological well-being message board.

For example, ethnography could empower you to foster a mind-boggling, detailed depiction of the social ways of behaving of the gathering by submerging yourself locally, as opposed to simply seeing from an external perspective, to explore the way of behaving, language, and convictions of a secluded Amazonian clan.

Because the idea of ethnography typically embraces an inductive, subjective, and interpretive research approach. There are certain exemptions for this standard, for example, David Shafer’s idea of quantitative ethnography.

Archival research –¬†The authentic examination is the last, yet not the least. A document research procedure utilises prior materials, and importance is then evolved through examining this information. This approach can use assets like original copies and reports and is appropriate for verifiable exploration.

For example, you could involve middle age original copies and archives as your principal wellspring of information on the off chance that you were keen on how individuals had an outlook on evidently heavenly occasions at that point. As may be obvious, there are various choices for research methodologies. Your venture’s most ideal choice will still be up in the air by your exploration’s objectives and goals and the choices you make on your examination approach.

Onion Layer 4: Choices

They might have been somewhat more unequivocal, wouldn’t you say? The following layer of the review onion is named decisions. Anyway, picking the number of subjective or quantitative information types, you’ll utilise in your exploration is all that should be finished in this layer. Mono, blended, and multi-technique are the three other options.

We should check them out now.

If you select a mono method, you will just utilise one kind of information, either subjective or quantitative. For example, suppose you needed to survey members’ points of view and assessments of the caf√©. In that case, you could use a subjective procedure while leading a review investigating how a local area had an outlook on a specific pizza eatery.

You would utilise a blended techniques procedure if you utilised quantitative and subjective information. Involving, for example, involving presentation as an aide, you could likewise need to decide the number of inhabitants of a local area that devour specific pizza assortments. To achieve this, you might lead a review to accumulate quantitative information, examine the discoveries measurably, and produce quantitative outcomes notwithstanding your subjective ones.

Multi-strategy comes last. Rather than just a single quantitative procedure and one subjective methodology, you would utilise a more impressive assortment of approaches while utilising a multi-strategy approach. For example, topical and content examinations are two instances of subjective strategies that may be utilised in a review that looks at documents from a specific culture. You could likewise utilise quantitative strategies to examine mathematical information.

The ideal choice here will depend on the sort of your examination as well as your exploration objectives and goals, very much as it does with the wide range of various levels of the exploration onion. There is likewise the down-to-earth element of reasonability, or, all the more explicitly, what kind of information can you access given your constraints.

Onion Layer 5: Time factor

The fifth and last layer of the onion is level time. Here you look at how the events in your story are connected in time. Could it be said that they are occurring at the same time? With hardly a pause in between? Over a significant period? Flat time is a significant component in understanding the occasions of your story and how they fit together. Ponder how you could feel while wasting time via virtual entertainment. I’m keen on investigating images’ language and how it changes through time. You would have to accumulate information for this review at different time frames, potentially more than half a month, months, or even years. Subsequently, you would utilise a longitudinal period. While analysing changes and advancements over time, this choice is beneficial.

All things being equal, you would utilise a cross-sectional time skyline to explore the language utilised in images at a particular second, say in 2020. Here information is assembled at a solitary second in time. Like this, your objective isn’t to follow the development of a language yet rather to distinguish its present status. The emphasis is on the time of assortment, not the information. In this manner, it may be subjective, quantitative, or a blend of both. The essential choice standards for picking the time skyline are the idea of your exploration and your examination points and targets, much like the wide range of choices. Moreover, you should consider common sense contemplations, for example, how much time you need to complete your exploration, especially on the off chance that you are composing a paper or proposition.

Onion Layer 6: methods and strategies

The strategies and methods that will be employed to gather and analyse data make up the sixth layer of the research onion. Choosing the study design, data collecting strategies, and data analysis methodologies are all part of this process. This layer also involves ethical considerations and ensuring that the research is feasible. Finally, we arrive at the centre of the onion, when decisions about particular approaches and procedures must be made based on the research’s actual practical considerations.

Here, precisely, you’ll:

  • Choose what information you’ll gather and how you’ll get it, such as if you’ll run a survey. How about confidential interviews?
  • Decide on your sampling strategies, such as convenience, random, or snowball sampling.
  • Choose the data analysis method that you’ll use to address your study issues.
  • Create the tools you’ll need for your research, like questions for surveys or interviews.

The philosophy, research strategy, research methodologies, and time horizon are just a few of the various layers of the research onion that must coexist harmoniously with these methods and procedures.

For instance, it’s unlikely that you’ll utilise interviews to collect your data if you’re employing a deductive, quantitative research technique because surveys are far better suited for obtaining high-volume, numerical data. You must thus ensure that the decisions you make at each layer of your onion are consistent with the others and, more crucially, that they are compatible with the aims and objectives of your study.

 Let’s Recap: Research Onion

The research onion outlines the numerous interwoven choices you’ll need to make while creating your research strategy. These include:

  • Your research’s research philosophy is the collection of assumptions that underpin positivism, interpretivism, and pragmatism.
  • Research methodologies, including inductive, deductive, qualitative, and quantitative methods.
  • Research strategies, including experimental, action, case study, and other research methods.
  • Options: whether to utilise a single method, a combination of methods, or many approaches.
  • Time factor – the number of cross-sectional or longitudinal time points at which you will collect your data
  • Methods and processes for data collection, analysis, sample techniques, etc.

You should start cooking now that the onion has been peeled. The most crucial thing to remember is that creating your research technique begins with clearly defining your research aims and objectives. So, before you start peeling, be sure they are.

Chapter 5: How To Write The Methodology Chapter

In the methodology section of a dissertation, the author describes the methods for gathering data, the structure of the study, and the methods for analysing the data. This chapter should provide enough detail for the reader to understand how the study was conducted and how the data was collected and analysed.

Overview: The Methodology Chapter

As the name suggests, the Methodology Chapter tells the reader how the study was conducted. In addition, it should provide the research plan and the overall strategy you will use to answer your research questions.

The Methodology Chapter is essential because it tells the reader how the data was collected and analysed. It must also describe the sampling strategy, data gathering techniques, data analysis techniques, and study design.

The study design, the sampling technique, the data collecting methods, and the data analysis procedures should all be described in detail in a well-organised and appropriate methodology chapter. In addition, it should be devoid of prejudice and inaccuracies.

So, what exactly is the methodology chapter?

In your technique chapter, you should discuss your decisions about your research design and the philosophical foundations for your study. The purpose of the methodology chapter is to explain in detail to the reader how your study was designed and to support your design decisions.

The methodology chapter should thoroughly explain and support your decisions regarding the research design. For instance, the type of study you conducted, such as qualitative or quantitative, the methods you used to collect and analyse your data, and the people or places you drew your data from (sampling). Later in this piece, we’ll go over all the major design decisions.

Why is the methodology chapter important?

The methodology chapter is important because it sets out the researcher’s stall regarding how they approached the research project, their methods, and how they analysed the data. This is important in establishing the trustworthiness and credibility of the research findings. Additionally, it enables other researchers to duplicate the work if they choose to.

The methodology chapter is also important because it proves that you comprehend study design theory, which gives you points. This chapter is crucial since it enables you to demonstrate to the marker that you are knowledgeable in your field and that your findings are credible. A lousy research design or technique would lead to unsatisfactory results.

The methodology chapter is crucial since it allows you to explore any methodological challenges or difficulties you encountered while conducting your study and explain how you dealt with them. Furthermore, it’s critical to transparently identify your study’s weaknesses and limits while emphasising the research’s importance despite these drawbacks. Once more, this indicates your comprehension of research design, which will result in points for you. Later on in this post, we’ll go into more detail about restrictions.

How to write up the methodology chapter

There is no one correct way to write a methodology chapter, as the approach will vary depending on the research design and methods used. However, some key elements should be included in all methodology chapters. These comprise an outline of the study design, the methodologies used, the techniques used to gather the data, and the techniques used to conduct the analysis. The chapter should also discuss the study’s limitations and the ethical considerations involved.

Before starting on your methodology chapter, it is essential to create a rough outline to have a clear direction for your chapter. Do not start writing without a clear direction because this is likely to cause disjointed work, which, as a result, may take a lot of time rewriting.

Here, we are going to discuss the generic structure of a methodology.

  • Introduction

Like any other chapter in your dissertation, the methodology chapter should also introduce briefly. A methodology’s introductory part will normally offer a brief summary of the study topic and research objectives. A review of relevant literature will also be provided, as will a synopsis of the study questions or hypotheses. The introduction is essential in reminding the reader of your study’s focus.

It’s helpful to frontload this information to remind the reader of the goals you have for your design and methodology, as we have frequently covered this site. Your research design must also align with your study aims, objectives, and questions.

  • Research Design

An extensive explanation of the research design employed in the study should be included in the methodology’s research design section. This should include a description of the research problem, the research questions that were used to guide the study, the research hypotheses that were tested, the research methodology that was used, the data collection procedures that were used, and the data analysis procedures that were used.

Let’s examine the most frequent design decisions you’ll have to make.

Design choice 1: Research philosophy

The guiding principles for how information about a phenomenon should be obtained, analysed, and applied are referred to as research philosophy. You must comprehend the philosophy you choose and its rationale because it will act as the foundation for your study and guide all other decisions regarding the research design.

Before choosing any research design options, take the time to clarify this if you aren’t sure.

Although there are many other research theories, positivism and interpretivism are two that are frequently used.

In quantitative studies, positivism is frequently the underpinning research philosophy. The researcher can see reality objectively since just one reality exists, regardless of the observer.

In contrast, interpretivism, frequently the underpinning research philosophy in qualitative investigations, assumes that each observer’s perception of reality is distinct from another. Thus, reality is perceived subjectively. Even though they are only two philosophies, they show two quite distinct approaches to research and significantly influence all the decisions made regarding the research design. As a result, you must describe and defend your research philosophy in detail at the beginning of the methodology chapter because it serves as the foundation for the remainder of the chapter.

Design choice 2: Research type

The second subject you typically include in your techniques section is the type of study. Start by stating if the research you performed was inductive or deductive. These studies often adopt an exploratory strategy since inductive inquiry builds theory from the ground up. On the other hand, deductive research starts with a pre-existing hypothesis and builds on it with obtained data; consequently, these investigations often use an affirmative strategy.

In connection with this, you must specify if your study uses a methodology based on qualitative, quantitative, or mixed methodologies. Make sure your selections are well connected since, as we’ve already said, there’s a strong connection between them and your research philosophy. Once more, while you write this part up, keep in mind to explicitly defend your decisions because they serve as the basis for your study.

Design choice 3: Research Strategy

In this section, you must outline your research strategy. The goals of your inquiry will determine the research methodology you choose. Let’s examine two of these experimental and ethnographic in more detail and compare them.

Experimental research employs the scientific method and consists of two groups: an experimental group and a control group in which no variables are altered. This type of research is conducted strictly with predetermined rules in controlled, artificial environments, like a laboratory. Because it provides strict environmental control, experimental research typically helps the researcher demonstrate causation between variables. Therefore, it may be a good alternative if one of your study’s objectives is to identify or quantify cause and effect.

Contrarily, ethnographic research entails witnessing and documenting individuals’ experiences and viewpoints in their natural settings. Or, to put it another way, in a chaotic setting. This naturally indicates that if your goal is to determine cause and effect, this study technique would be significantly less effective; yet, if your goal is to investigate and analyse a group’s culture, it would be pretty beneficial.

Design choice 4: Time factor

The next subject you must discuss in your approach chapter is the time horizon. Here, longitudinal and cross-sectional analyses are the two choices. Or whether the information for your study was gathered all at once or over several hours.

Your decision here will again be influenced by your research’s goals, objectives, and questions. For instance, you may use a longitudinal time horizon if your goal is to evaluate how a particular set of people’s attitudes on a subject evolve.

.Another significant aspect is practical limitations, or if you have the time required to take a longitudinal method. Remember that your degree program’s time constraints will frequently lead you to adopt a cross-sectional time horizon.

Design choice 5: Sampling Strategy

It would be best if you then talked about your preferred sampling plan. Probability sampling and non-probability sampling are the two most often used sampling techniques. Non-probability sampling calls for the non-randomised-randomised selection of participants, whereas probability sampling calls for the random selection of participants from a population.

What you hope to accomplish with your study will determine which sampling strategy is best. Specifically, whether or not you’re attempting to draw conclusions that apply to a population. As it may sometimes be difficult to obtain access to a genuinely random sample, practical considerations and resource limitations also play a significant part in this.

Design choice 6: Data collection methods

In this section, you must describe how you plan to get the required data for your investigation. Whether you aim to collect qualitative or quantitative data will determine the data collecting approach you use.

Quantitative research often uses surveys, data from lab instruments, analytics software, or pre-existing databases. On the other hand, qualitative research frequently uses data-gathering techniques, including participant observation, ethnography, focus groups, interviews, and participant observation.

Design choice 7: Data analysis methods

Analysis methods are the last important design decision you must make. In other words, how will you approach data analysis after you have gathered your data? Here, it’s crucial to be precise with your analytical approaches and methodologies. Additionally, it would be best if you justified every decision you make, as with all others in this chapter.

The sort of study you’re conducting will have a significant impact on what you specifically talk about here. Standard methods of analysis for qualitative investigations include content analysis, theme analysis, and discourse analysis. Descriptive statistics are usually used in quantitative investigations, and inferential statistical methods are also frequently used.

.This part should also include the data preparation process and the tools you employed for the analysis. For instance, preliminary quantitative data processing is frequently necessary, such as eliminating duplicates and insufficient replies. Always be sure to describe your actions in detail, as well as your motivations.

  • The methodological limitations

Given your restrictions, there will always be flaws between the ideal research design and what is feasible and practicable. As a result, in this area of your technique chapter, you will talk about the trade-offs you made and why they were appropriate in the current situation.

The methodological limitations section of your dissertation is where you discuss the limitations inherent in your study and how they may have affected your results. This is an important section to include in your dissertation as it shows that you are aware of the limitations of your study and that you have taken them into account in your results.

  1. There are several different types of limitations that you may need to discuss, including.
  2. The sample size of your study. If your study only included a small number of participants, this may have limited the power of your results.
  3. The geographical location of your study. If your study was conducted in one specific location, this might not be representative of the wider population.
  4. The type of participants in your study. If your study only included participants from one specific group (e.g. students), this may limit the generalizability of your results.
  5. The type of data collected in your study. If your study only used self-report data, this may limit the validity of your results.
  6. The length of time over which your study was conducted. If your study was conducted over a short period, this might limit the external validity of your results.
  7. The methods used in your study. If your study used a qualitative methodology, this might limit the generalizability of your results.

It is essential to discuss the implications of these limitations in your dissertation and how they may have affected your results. However, it would be best if you also highlighted that despite these limitations, your results are still valuable and provide insight into the research question.

It’s crucial to point out the limitations of your study in this part. Attempting to conceal them is pointless. Don’t be afraid to be critical because doing so will show your marker that you understand study design very well. Don’t exhaust your study, though, at the same time. List the restrictions, explain why they were warranted, describe how you minimised their effects as much as possible, and explain how your study is still valuable despite these restrictions.

  • Concluding Summary

The methods chapter must now be concluded with a concise summary. This part should briefly summarise what you’ve delivered in the chapter. For example, if your institution advises utilising a particular model, it may be helpful to create a diagram to summarise the critical design choices in this case.

This part must be concise, no more than a paragraph or two. Ensure to include the material you covered in your chapter in your ending summary and avoid adding additional information.


That sums up the methods chapter. As we’ve already discussed, each university may have somewhat different requirements for this chapter’s content and organisation, so verify with yours before you start writing. If at all feasible, look for dissertations or theses written by past students of the degree programme; this will give you a clear idea of the standards and expectations for the methodological chapter.

Additionally, remember the methodology chapter’s guiding principle: justification of every decision! To support your reasons, include a clear “why” for each “what” and cite reliable methodological manuals or academic publications.

If you want assistance with your methodology chapter, just contact us and we will be happy to help!

Chapter 6: Qualitative Data Analysis Methods - The ‚ÄúBig 6‚ÄĚ Methods

If you’re new to the field of research, qualitative data analysis might be scary. So much jargon, so many vague, fluff notions. In this section, we’ll go over the most common analysis methodologies one by one so you may tackle your analysis with skills and ease.

So, let us get to it!

What is qualitative data analysis?

Qualitative data analysis examines, transforms, and interprets data to generate new understanding or knowledge. It is an iterative process that involves making sense of data, identifying patterns and connections, and formulating hypotheses. Qualitative data analysis aims to produce rich and detailed descriptions of the phenomena under study. The data collected in qualitative research is often complex and multi-dimensional, making it challenging to analyse. Qualitative data analysis often requires a creative and inductive approach, as researchers must generate new understanding from the data. There are many approaches to qualitative data analysis, and there is no one right way to do it. Most importantly, the technique must be suitable for this research and the study topic.

So, how is qualitative data different from quantitative data?

Data obtained by qualitative techniques such as focus groups, interviews, and observations is referred to as qualitative data. This information is usually more detailed and comprehensive than quantitative information. Surveys and experiments are two approaches for gathering quantitative data. This data is typically more numerical and can be used to test hypotheses.

Is qualitative data simpler to analyse than quantitative data?

No, not at all. Analysing and evaluating qualitative information may be hard and time-consuming in many ways. After the data collecting process, you’ll probably have a lot of pages of content data or a lot of audios to listen to. You could have small subtleties of conversations or talks dancing around in your head or jotting down in sloppy field notes.

This paper will look at the overall methods used to cope with qualitative data. We won’t go¬†into considerable detail or describe every conceivable qualitative approach; instead, we’ll offer you the big picture. These approaches are applicable to both primary and secondary data.

The Qualitative Data Analysis Methods ‚ÄúThe Big 6‚ÄĚ

Content analysis, theme analysis, discourse analysis, grounded theory, narrative analysis, and interpretive phenomenological analysis are the six basic methodologies for analysing qualitative data. Each method has strengths and weaknesses and can be used in different ways to answer different research questions. Let us briefly discuss them to give you a rough idea before diving into it.

  1. Content analysis is a technique for analysing textual data that involves recognising and categorising relevant content units. This method can be used to analyse written and spoken data and to study a wide range of phenomena.
  2. Thematic analysis is a technique for detecting and analysing data patterns. This technique may be used to find themes in both spoken and written material and is frequently used to analyse interview data.
  3. Discourse analysis is a method for analysing spoken or written language in terms of how it is used to construct meaning. This method can be used to study a wide range of phenomena, including social interaction, decision-making, and knowledge production.
  4. Grounded theory is a method for developing a theory from data. This method is often used in qualitative research and can be used to develop a theory about a wide range of phenomena.
  5. Narrative analysis is a qualitative data analysis approach that examines tales, interviews, and other types of data to determine how individuals make meaning of their experiences. This method can be used to understand how people construct meaning in their lives, make decisions, and interact with others. In addition, the narrative analysis can be used to understand how power and inequality are reproduced in society.
  6. The Interpretative Phenomenological Analysis is a qualitative data analysis process used to learn about people’s lives. This method is used to understand how individuals make sense of their experiences and the world around them.

So, let us dive onto them.

QDA Method 1: Content Analysis

The social sciences frequently employ the qualitative data analysis technique of content analysis. It is a way of analysing data based on its content rather than on its structure. This means that content analysis can be used to analyse data that is not numerical, such as text, images, or videos. Data obtained using qualitative approaches, such as focus groups, or interviews are frequently analysed using content analysis. It may, however, be used to analyse data gathered through quantitative approaches such as surveys.

There are several different ways to analyse data using content analysis. One common way is coding, which involves assigning codes to the data so it can be analysed systematically. Another common way to analyse data using content analysis is thematic analysis, which involves identifying and analysing the themes in the data. Content analysis is a powerful tool that can be used to understand a wide variety of data. It is a flexible method that can be used to answer a variety of research questions.

While content analysis is valuable, it does have certain drawbacks. One of the biggest problems with content analysis is that it might take a lot of time because of all the reading and rereading that is necessary. Furthermore, it is frequently charged with overlooking significant communication subtleties due to its varying emphasis on qualitative and quantitative components.

Additionally, content analysis has a propensity to ignore events that took place before or after the time period it is focusing on. This is simply something to consider; it’s not always a negative thing. So have these things in mind if you’re considering conducting some content analysis. Do not be put off by the drawbacks of any analysis method.

QDA Method 2: Thematic Analysis

In a qualitative data analysis technique called thematic analysis, the data is sorted to find recurring themes or patterns. This can be done by hand or with specialised software. Once themes are identified, they can be further analysed to understand their implications. Thematic analysis is often used in research studies to analyse interview data or open-ended survey responses. It may, however, be used to analyse other kinds of qualitative data.

 Thematic analysis is a flexible method that can be used in various ways. Common approaches include coding data manually or using specialised software to identify themes, conducting a thematic analysis by hand or with software, and using a deductive or inductive approach. Thematic analysis has several advantages. It may be used to many data sources and is a fairly simple technique to master. It is a versatile approach that may be modified to meet the demands of the researcher.

¬†There are also some limitations to consider. Thematic analysis can be time-consuming, mainly if data are coded manually. Additionally, the interpretation of results can be subjective and may vary depending on the researcher’s perspective. Despite its shortcomings, thematic analysis is a useful qualitative data analysis tool for identifying common themes in data. When utilised appropriately, it can give insights that would otherwise be impossible to gain.

QDA Method 3: Discourse Analysis

Discourse analysis is a qualitative research approach that examines written or spoken language to find hidden meanings and implicit assumptions. Discourse analysis is a technique for determining how language is used to establish and sustain social relationships. It can be used to study how people use language to communicate their thoughts and feelings, how they interact with each other, and how they make sense of their experiences.

 Discourse analysis can study any form of communication, including face-to-face conversations, written texts, media broadcasts, and even nonverbal communication such as body language and facial expressions. It is a flexible method that can be adapted to fit the needs of any research question. However, discourse analysis is a complex and detailed method, and it is essential to remember that no single approach is suitable for every research question.

When using discourse analysis, researchers must avoid making assumptions about what people mean based on their words alone. Instead, it is essential to consider the context in which communication occurs and the power dynamics between the people involved. Discourse analysis is an effective method for revealing hidden meanings in language. It may be used to investigate how individuals express themselves, engage with one another, and make meaning of their experiences.

Discourse analysis has a wide range of possible applications since social effects on how we communicate with one another are so many. Naturally, this implies that in order to avoid falling into a looping rabbit hole, you must have a relevant research topic in mind when you analyse your data and look for patterns and themes.

Discourse analysis might take a while since it requires sampling the data until it reaches saturation or there is no longer any fresh knowledge or insights. However, it goes without saying that this is precisely why discourse analysis is so effective. When evaluating the QDA approach, keep these things in mind.

QDA Method 4: Grounded Theory

A qualitative research strategy called grounded theory was developed by sociologists in the 1960s. Other disciplines, such as anthropology, psychology, and education, later adopted the methodology. The central tenets of grounded theory are that data should be collected and analysed concurrently and that the analysis should be focused on generating theory from the data.

The generated theory should be “grounded” in the data, meaning that it should be based on what the data reveal. There are four main steps in grounded theory analysis: defining the research question, data collection, data analysis, and theory generation.

  1. The first step in grounded theory is to define the research question. This is done by identifying the phenomenon that you want to study and the scope of the study. For example, you may want to study how people experience grief. Once the research question is defined, data are collected.
  2. Data collection typically involves conducting interviews or focus groups with knowledgeable individuals about the phenomenon under study.
  • Data analysis involves coding the data and identifying patterns and relationships.
  1. Theory generation involves developing hypotheses based on identified patterns and relationships.

Grounded theory is considered one of the “big six” qualitative data analysis methods, along with ethnography, phenomenology, case study, historical methods, and content analysis.

The grounded theory also has some drawbacks. Some argue that Grounded Theory suffers from a problematic circularity. To prevent bias in your interpretation, you should know as little as possible about the research topic and population. In many circumstances, however, it is deemed risky to approach a study topic without first examining the current literature.

Grounded theory is still a well-liked (and useful) choice. As a consequence, because it enables you to start at the bottom and work your way up, it’s a particularly effective strategy for researching a subject that is entirely new or has very little current study.

QDA Method 5: The Narrative Analysis

The narrative analysis is a qualitative data analysis approach that examines tales and the events that comprise them. Narrative analysis is concerned with how people understand their relationship with the world around them, as well as how they transmit that knowledge to others. It is a way of understanding how people create and share meaning. Narrative analysis is a way of understanding, interpreting, and making sense of people’s stories about their lives. It is a form of qualitative research that uses storytelling to understand human experience.

Narrative analysis is used by researchers to examine the tales people tell about their life and the events that comprise those stories. They are curious about how people make sense of their lives and the world around them, as well as how they transmit that knowledge to others.

Narrative analysis can be used to study a wide range of topics, including people’s relationships, health and well-being, work and education, and leisure activities. It can also be used to study how people interact with technology and how they make decisions. Researchers who use narrative analysis often use various methods to collect data, including interviews, and observations. They may also use written sources, such as diaries and journals.

There are limitations to other analytical strategies, including the narrative process. Sample sizes are sometimes small because collecting tales requires time. Because there are so many different social and lifestyle factors that might affect a person, it can be challenging to duplicate narrative analysis in future research. As a result, it is challenging to confirm the results of some of this research.

The results may also be significantly influenced by researcher bias in this case; thus, you must use this method with extreme caution and be very aware of any bias you could introduce into your research. Despite these drawbacks, story analysis is a crucial qualitative technique; keep this in mind and stay away from generalisations.

QDA Method 6: Interpretive Phenomenological Analysis

The Interpretative Phenomenological Analysis (IPA) technique investigates how people make meaning of their lived experiences. It is particularly concerned in how individuals make sense of their surroundings and how this influences their attitudes and behaviours. IPA is a flexible methodology that can be used in various settings and with various data sources. It is often used in psychology and counselling but has also been used in other disciplines such as education, sociology, and anthropology.

IPA is a relatively new methodology developed in the 1980s. It has its roots in phenomenology, a philosophical tradition that emphasises the importance of understanding how people experience the world. IPA and other qualitative methodologies like grounded theory and story analysis share many similarities. IPA is a flexible methodology that can be adapted to various research questions and contexts. However, it is typically used with small-scale studies, as it is a time-consuming and resource-intensive methodology.

 IPA studies typically use semi-structured or unstructured interviews as their primary data source. It is also possible to use additional data sources like field notes, observations, and papers. The data analysis process in IPA is inductive, meaning that it starts with the data and proceeds to develop themes and concepts. The data are typically analysed using various methods, including coding, thematic analysis, and reflexivity. In addition, the data analysis is often iterative, meaning that it is done in multiple stages, and the data are analysed multiple times.

 IPA aims to produce rich, detailed descriptions of how people make sense of their lived experiences. IPA studies often produce thick, detailed descriptions that can be difficult to interpret. However, these descriptions can be precious in helping to understand the complexities of human experience.

How to choose the proper analysis method

You’re undoubtedly wondering, “How do you select the correct one?”

The ideal qualitative analysis technique is defined mostly by your study goals, objectives, and questions. The project determines the ideal tool for the work. For example:

  1. There are several factors to consider when choosing suitable qualitative data analysis methods. The first is the type of data you have collected. This will determine what methods are available to you and which are most appropriate. For example, if you have collected interview data, you might use content or thematic analysis. On the other hand, if you have collected observational data, you might use ethnographic methods or grounded theory.
  2. The second factor to consider is the purpose of your research. This will help you identify the most appropriate methods to answer your research questions. For example, phenomenological approaches might be used to investigate people’s perceptions of a certain phenomenon. On the other hand, if you are interested in understanding the social processes at work in a particular setting, you might use ethnographic methods.
  • The third factor to consider is the resources you have available. This includes the time and money you must invest in your research. Data analysis may be time-consuming, so be honest about how much time you can devote to it. You might need to choose less resource-intensive methods if you have a limited budget.
  1. The fourth factor to consider is your skills and expertise. This includes your theoretical understanding of qualitative methods and your practical experience using them. If you are new to qualitative research, you might want to start with a less complex method such as content analysis. If you have more experience, you might feel confident using a more complex method such as grounded theory.
  2. Finally, you need to consider the context in which you will be conducting your research. This includes the setting, the participants, and the culture. These factors can influence the data you collect and the methods you use to analyse it. For example, if you are studying a sensitive topic, you might need to use methods that protect the anonymity of your participants. If you are studying a culture unfamiliar to you, you might need to use methods that help you understand the meanings and values essential to that culture.

Because each of these research aims is unique, different analytic methodologies would be acceptable for each. Remember that each strategy has its own set of benefits, drawbacks, and overall constraints. There is no perfect analytical method. As a consequence, while it is time-consuming, it frequently makes complete sense to apply more than one strategy.

All of these approaches, as we’ve seen, rely on coding and thematic processes, but the goals and procedures of each analytical approach differ greatly. As a result, having a defined aim is essential before settling on an analytical technique.

Before choosing a strategy, analyse your research’s objectives, aims, and questions to determine what you hope to learn. Never choose a technique just because you enjoy it or have used it before; your analytical approach (or procedures) must be consistent with the overall goals and objectives of your study.

Let’s Recap

In this essay, we looked at the six most frequent qualitative data analysis methodologies., notably:

  1. Content Analysis – A qualitative data analysis approach that involves classifying and classifying textual data is content analysis. This can be done either manually or using software.
  2. Thematic analysis – Thematic analysis is a qualitative data analysis approach used to uncover, analyse, and understand patterns in data. Thematic analysis is often used to analyse interviews, focus group data, and other forms of qualitative data.
  3. Discourse analysis – Discourse analysis is a qualitative data analysis approach that examines how individuals speak with one another. It focuses on the structure and content of communication and the context in which it takes place. Discourse analysis can study written texts, spoken interactions, or any other form of communication.
  4. Grounded theory analysis – The grounded theory approach is a qualitative data analysis method for developing data-driven theories. This method is used to generate hypotheses and concepts that are based on data collected from research participants. Next, the data is analysed to identify patterns and relationships between concepts. Theories are then developed to explain these patterns and relationships.
  5. Narrative analysis – Narrative analysis is a way of analysing qualitative data that entails reading and evaluating narratives or tales. This method can analyse both fictional and non-fictional stories to understand the characters, plot, and themes.
  6. Interpretive Phenomenological Analysis – The Individual Participant Analysis (IPA) approach is a qualitative research methodology that focuses on understanding meaning from the perspective of individual participants. The goal is to learn how participants interpret their experiences and the world around them. IPA is typically used to study lived experiences, personal meanings, and subjectivity.

Chapter 7: Five [5] Mistakes In Qualitative Interviews

A dissertation requires time, expertise, and knowledge to design. Without a precise aim and methodology, your results may likely be skewed, giving you a false impression of what you were attempting to achieve. While it’s crucial to follow the correct technique in the dissertation, it’s just as crucial to avoid making mistakes that could skew the results. The five most common issues students face when undertaking interviews for qualitative research are:

  1. Not knowing how to structure an interview
  2. Not knowing how to ask probing questions
  3. Not knowing how to build rapport
  4. Not knowing how to listen
  5. Not knowing how to take practical notes

These issues can lead to problems during the interview process and may lead to less valuable data being collected.

  1. Not knowing how to structure an interview

One of the most common issues students face when conducting interviews is not knowing how to structure an interview. This can lead to the interview feeling disorganized and unfocused, making it difficult for the interviewer to obtain the necessary information.

  1. Not knowing how to ask probing questions

Another common issue is not knowing how to ask probing questions. This can lead to the interviewer not getting the level of detail they need from the interviewee and may cause the interview to feel superficial.

  1. Not knowing how to build rapport

Another common issue is not knowing how to build rapport with the interviewee. This can make the interviewee uncomfortable and less likely to open up, leading to less valuable data being collected.

  1. Not knowing how to listen

Another common issue is not knowing how to listen effectively during the interview. This can lead to the interviewer missing important information and may cause the interview to feel rushed or unproductive.

  1. Not knowing how to take practical notes

Finally, another common issue is not knowing how to take practical notes during the interview. This can make it difficult for the interviewer to remember what was said and may lead to important information being lost.

Chapter 8: Qualitative Data Analysis 101

When most students hear about Qualitative Data Analysis, they become fearful, which is understandable since quantitative analysis is a complex topic. The good news is that, while quantitative data analysis is a vast subject, getting a functional grasp of the fundamentals isn’t difficult, even for those who dislike numbers and arithmetic. In this piece, we’ll break down the quantitative analysis into manageable, bite-sized bits so you may approach your study with confidence.

What exactly is quantitative data analysis?

Quantitative data analysis is analysing numerical data to conclude the underlying processes that generated the data. The analysis involves using statistical techniques to identify data patterns and trends and infer the relationships between different variables. Various research problems can be addressed using quantitative data analysis, such as:

-What is the average level of income in a particular country?

 -What factors are associated with higher levels of educational attainment?

-What is the relationship between economic growth and crime rates?

The statistical techniques used in quantitative data analysis vary depending on the data analysis type and the research question being addressed. However, some standard quantitative data analysis methods include regression, correlation, and time-series analysis.

What is a quantitative analysis used for?

Quantitative data analysis is used for a variety of purposes, including:

  • Describing the distribution of variables in a dataset
  • Exploring relationships between variables
  • Testing hypotheses about relationships between variables
  • Making predictions based on relationships between variables
  • Depending on the data being examined and the research’s specific objectives, quantitative data analysis may be used to address a wide range of topics. For example, quantitative data analysis can be used to:
  • Describe the distribution of a single variable: How many people are in each age group? What is the average income of people in each income bracket?
  • Explore relationships between two or more variables: Do people with higher incomes tend to live in more expensive neighbourhoods?
  • Test hypotheses about relationships between variables: Do people with college degrees tend to live in more expensive neighbourhoods?
  • Make predictions based on relationships between variables: If a person’s income increases, how will their spending patterns change? How will a person’s income change if moving to a more expensive neighbourhood?

How does Quantitative analysis work?

Unsurprisingly, Statistics are necessary for quantitative data analysis since it involves analysing numbers. Quantitative analysis is powered by statistical analytic techniques, which might involve anything from straightforward calculations to in-depth research.

There are many ways to analyse quantitative data, but standard methods include statistical, regression, and correlation analysis. Calculating measures of dispersion like range, variance, and standard deviation, as well as measures of central tendency like mean, median, and mode, are just a few examples of how statistical analysis may be employed. In addition, regression analysis can examine the relationships between different variables, and correlation analysis can assess the strength of those relationships.

The two ‚Äúbranches‚ÄĚ of quantitative analysis

As previously said, Statistical analytic techniques feed quantitative analysis. Descriptive and inferential statistical approaches are also employed. Depending on what you’re seeking to discover, you may solely utilise descriptive statistics in your study or a combination of both. In other words, it depends on your study questions, objectives, and goals. Later, I’ll go through how to pick your approaches.

So, what are descriptive and inferential statistics?

Before we explain what descriptive and inferential statistics are, we must first understand population and sample concepts.

First, the population is the number of individuals in a given area. So, for example, if we were researching homeowners in the UK, then the population would be all homeowners in the UK.

However, it is less probable that they will interview all homeowners in the UK. So, therefore, they are going to get access to a few hundred owners. So these chosen group of homeowners that will be interviewed will represent the larger population, and this small group is what we call the sample.

So, to get a clear understanding, the population is the entire group of people you are interested in researching, while the population is the smaller population that is accessible.

So why is this concept important?

While descriptive statistics focus on characterising the sample, inferential statistics aim to deduce information about the population from the outcomes of the sample. While descriptive statistics focus on characterising the sample, inferential statistics aim to deduce information about the population from the outcomes of the sample.

Descriptive Statistics

As the name indicates, descriptive statistics provide an essential yet crucial function in your study by outlining the data gathering process. They help you understand the peculiarities of your sample, in other words. Descriptive statistics, as opposed to inferential statistics, are solely interested in the details of your sample and do not make any attempts to generalise or make predictions about the entire population.

When conducting your analysis, you’ll start with descriptive statistics and work up to inferential statistics. However, depending on your study’s objectives and research questions, these could be the only statistics you use.

What kinds of statistics are covered in descriptive statistics?

Descriptive statistics are used to summarise data. This includes finding the mean, median, mode, and range. It also includes finding the standard deviation and variance.

  1. Mean- The most popular way to quantify central tendency is to use the mean, obtained by adding up all the values in a data collection and dividing the result by the total number of values. Given that it provides a thorough picture of the data set, the mean is frequently employed to represent data sets containing many values.
  2. Median – A data set’s median describes its centre tendency. When a data collection is ordered from least to most significant, this value is in the centre. Because it is unaffected by outliers, the median is a valuable metric to employ when there are any in the data set.
  3. Mode – The most prevalent value in data collection is indicated by a measure of central tendency called the mode. The mode is frequently utilised when dealing with categorical data, representing several item classes or human population classifications.
  4. Range – A dispersion measurement is determined by comparing a data set’s highest and lowest values. It is a simple calculation frequently used to provide a rapid overview of the range of values in a data collection. But the range is impacted by outliers, so it’s not necessarily the most accurate dispersion indicator.
  5. Standard deviation – The standard deviation, a statistical measure of variability, quantifies the variation of a collection of data around its mean. The standard deviation is calculated using the variance, which is the average square of the variances from the mean. The variability in the data set increases with increasing standard deviation. Standard deviation is a useful measure of variability because it is resistant to outliers, meaning that data points far from the mean will not significantly impact the standard deviation. Standard deviation is also helpful for comparing data sets with different means and for determining whether a data set is standard or not.

¬†The data set is located on the left. This table shows the bodyweight of ten persons. The descriptive data are on the right side. So, let’s take a look at them one by one.

  • First, we can see the mean weight of the group of people, which is 72.4 kilograms.
  • The second is the median, whose value is almost similar to the means. This means that the data recorded has a symmetrical distribution.
  • The third is the mode which is not recorded in the data set because each value has only been recorded once throughout the distribution.
  • Next up is the standard deviation, whose value is 10.6. Again, this value indicates that there’s quite a wide range of numbers. We can also note this by looking at the numbers, ranging from 55 to 90, which is quite a wide range.
  • Lastly is the skewness, which has a value of -0.2, indicating that the distribution is slightly negatively skewed. This is evident because the mean and the median are slightly different in their values.

As you can see, these descriptive statistics provide us with necessary information about the data set. But, of course, because this is a relatively tiny data set, we shouldn’t read too much into these figures.

Why do all of these numbers matter?

Although these descriptive statistics are all relatively straightforward, they are helpful for several reasons:

  1. They provide you access to your data’s macro and micro levels. They help you understand both the big picture and the fine details, in other words.
  2. They help you see possible issues with the data; for instance, if an average is significantly higher than you may have predicted or if responses to a question are wildly inconsistent, this can be a sign that you should double-check the data.
  3. Descriptive statistics help suggest which methods may be utilised because inferential statistical procedures depend on how skewed the data are.

Descriptive statistics are incredibly significant, even though the statistical procedures are pretty simple. Fortunately, at Skylink Research, we find students skipping through the descriptive to get to the more fun inferential approaches, producing some inferior results.

  • Inferential Statistics

As mentioned above, descriptive statistics are linked to a specific data set. On the other hand, inferential statistics aims to create assumptions about the population.

Researchers commonly use inferential statistics to produce two sorts of predictions:

  • Predictions concerning group differences include height variations between children sorted by favourite food or gender.
  • One illustration of a link between variables is the association between body weight and the quantity of yoga practised weekly.

In other words, using your sample data as a starting point, inferential statistics enables you to draw conclusions and forecast what you expect to find in the general population. As a result, inferential statistics are employed to evaluate hypotheses that anticipate changes or differences.

Of course, when working with inferential statistics, sample composition is critical. If your sample does not adequately represent the community under study, your results may be ineffective.

For example, if your population of interest is split 50/50, but your sample is 80/30, you can’t conclude the population based on your sample since it’s not representative. This is known as statistical sampling, but we won’t go there now.

What types of statistics are used in inferential statistics?

There are several statistical analysis methods within the inferential branch, and it would be hard to explain them here. So, let’s go through some of the most prevalent inferential statistical approaches so you can get a good start.

  1. T-Tests – To determine whether there are any statistical differences between two data sets’ means (averages), t-tests are used. Are their differences in their means, standard deviations, and skewness significant? Finding out how similar or different two sets of data are using this testing is quite helpful. For example, you may compare the mean blood pressure of two patients – one that has taken a new drug and one that has not – to see if they differ considerably.
  2. Correlational analysis- This study looks at the link between two variables. Does the other increase, decrease, or remain constant if one variable grows? For example, do ice cream sales rise if the average temperature rises? Although correlation analysis enables us to measure this relationship scientifically, we naturally expect some connection between these two variables.
  3. ANOVA ‚Äď Analysis of variance, or ANOVA, is the term. This test compares the means of many groups like a T-test, except ANOVA enables you to analyse multiple groups instead of simply two.
  4. Regression analysis ‚Äď Analysing relationships between variables using regression is akin to doing so through correlation. But establishing cause and effect between variables, instead of merely observing whether they move in tandem, requires more work. In other words, do the variables naturally move together due to another factor or does one cause the other to move? One does not automatically infer those two variables are related because they correlate.

These are only a few of the numerous inferential techniques available. Notably, every statistical method has a unique set of presumptions and restrictions. Some approaches, for example, operate solely with regularly distributed data, whilst others are mainly developed for non-parametric data. That is why descriptive statistics are so helpful.

How to choose the suitable analysis method

Two critical variables must be considered while selecting the appropriate statistical procedures:

  1. The type data
  2. Your research topic, questions and hypothesis

Let us discuss these two factors further:

The type of data –¬†The first thing you should consider is the data you’ve gathered. By data types, I mean the four measurement levels: nominal, ordinal, interval, and ratio. If you’re unfamiliar with the terminology, read this page to learn about the four levels of measurement.

Why does this matter?

Because various statistical approaches and procedures necessitate different sorts of data, This is one of the “assumptions” I described before; each technique has its own set of assumptions about the type of data. Some strategies, for example, work with categorical data, others deal with continuous numerical data, and others work with several data types.

If you apply a statistical approach that does not support the data type you have, the findings will be essentially worthless. So, make sure you understand what kinds of data you’ve collected. Once you have this, you can use it to see which statistical methods are compatible with your data types.

Suppose you haven’t yet gathered your data. In that case, you may work backwards to see which statistical approach will provide you with the most relevant insights and then construct your data collecting plan to acquire the appropriate data kinds.

The form of your data is another critical consideration. Is it customarily distributed or slanted to the left or right? Again, various statistical procedures work for different types of data; some are intended for symmetrical data, while others are intended for skewed data.

Research questions and hypotheses –¬†Your unique research questions and hypotheses should be considered next. Which statistical approaches and procedures you select will be highly influenced by the nature of your research questions and assumptions.

Descriptive statistics are typically all you need if you only want to understand the characteristics of your sample (rather than the entire population). For example, suppose all you want to do is compare the means and medians of variables in a group of people.

On the other hand, if you want to understand disparities between groups or correlations between variables and infer or anticipate population outcomes, you’ll probably require both descriptive and inferential statistics.

So, before considering which statistical approaches to utilise, you should be extremely clear about your research goals, study questions, and hypotheses.

Never incorporate a particular statistical approach into your study simply because you enjoy it or have some experience with it. All of the elements discussed here must be considered in your approach selection.

Let us Recap

We have covered a lot of ground in this section. So, let us remind ourselves about the key points:

  • The examination of numerical data using different statistical methods is known as quantitative data analysis.
  • Descriptive and inferential statistics are the two categories into which statistics are separated. While inferential statistics predict what will be discovered in the population, descriptive statistics describe your sample.
  • Standard deviation, range, skewness, mean, and median are typical descriptive statistical techniques.
  • Standard inferential statistical techniques include T-tests, ANOVA, correlation, and regression analysis.

When selecting statistical tools and techniques, keep in mind the type of data you’re using, your research objectives, and your hypotheses.

Chapter 9: Survey Design: Common Mistakes And Issues

The data you need for your dissertation, thesis, or research project may be gathered effectively through surveys. A good survey enables you to gather substantial amounts of meaningful data with (relatively) minimal work. You may encounter significant problems if your design is poor, though. In terms of survey design, there are a lot of typical errors that students make that we’ve seen over the years. We’ll discuss five of these expensive errors in this piece.

Overview: 5 mistakes that students make when designing their surveys

  1. Poor survey structure
  2. Poorly structured questions
  3. Inappropriate response types
  4. Unreliable and invalid measures
  5. Designing without consideration for analysis techniques

Let’s look at each of these mistakes.

  1. Poor survey structure

Poor survey flow and organisation are among the most frequent problems we see. Survey takers will be deterred from completing it if the survey is poorly constructed. Because of this, not many people will take the time to complete the survey, which might result in limited sample size and subpar or useless results. So let’s examine some recommended practices to ensure a solid foundation and a smooth flow.

  • Make sure your survey matches your study‚Äôs “golden thread”

The first stage might seem apparent, but it’s crucial to create survey questions closely related to your research question(s), goals, and objectives ‚ÄĒ or, to use another phrase, “your golden thread.” To address these essential ideas in your thesis, your survey must produce the data; if it fails to do so, you have a severe issue. Therefore, you must always keep your research’s central theme while designing your survey questions.

  • Make sure that your questions are listed in a logical order

When creating an effective survey, the sorts of questions you ask and the timing of your inquiries are crucial. Organise your questions logically and transparently to prevent losing responses.

Asking questions about exclusion in advance is often an intelligent approach. For instance, your first question should be one to ascertain the respondent’s gender if your study is centred on a facet of women’s life. Afterwards, you can ask questions about the major concepts or ideas, the dependent and independent variables, or both of your study before moving on to the exclusion criteria.

Lastly, the survey’s demographics-related items are often placed towards the conclusion. Regarding the traits of your respondents, these are the questions. It’s a good idea to include these questions towards the conclusion of your survey since respondents can become distracted by them while they complete the other questions in the survey. Including them after your survey makes it more likely that respondents will pay close attention to the questions about the primary research constructs.

  • When designing your survey, ensure that it is easy to use

Even though it might seem simple, while developing your survey, it is crucial to analyse the “journey” of your respondents carefully. In other words, when creating your survey, you must prioritise the user experience and engagement.

Having a clear introduction or cover page upfront is one method of creating a positive customer experience. It’s a good idea to state the approximate time needed to finish the survey on this introduction page. To aid respondents in understanding the context of each question or part in your survey, utilise headers and brief explainers. A progress indicator that shows how far along respondents are in finishing the survey is also beneficial.

Naturally, a survey’s performance depends on its readability. Keep the survey information as brief as possible because people prefer to abandon lengthy questionnaires. As a general rule, use straightforward, understandable language. In connection with this, thoroughly revise and proofread your survey before distributing it. Spelling, punctuation, and structure mistakes can significantly reduce your work’s trustworthiness and probably result in more respondents dropping out.

If you must use a technical phrase or industry jargon, define it first. The technical parts of your survey shouldn’t divert or perplex respondents. Additionally, establish a logical flow by grouping similar themes and shifting from generic to more specialised inquiries.

Additionally, consider the tools that respondents will use to access your survey. Making your survey mobile-friendly will enable more people to reply, which is quite advantageous because many people use their phones to conduct surveys. The mobile part of your survey should be handled by hosting it with a reputable service, but you should still try it out on a few different gadgets. Using a reputable survey platform will simplify the data collecting and the analysis of the survey results.

  • Priorities, ethics, and data privacy

The ethical guidelines are the final aspect to consider while creating your survey. Your nation’s ethics guidelines and data protection regulations must be followed in your survey design. You must abide by GDPR, for example, if you live in Europe. To allay respondents’ worries about the privacy and security of their information, it’s also crucial to emphasise that all data obtained will be managed and stored securely.

  1. Poorly structured questions

We also frequently run into issues with poorly written questions and assertions in survey design. There are several different ways that questions might be miswritten. Typically, they fit into four primary groups:

  • Leading questions
  • Vague questions
  • Loaded questions
  • Double-barrelled questions

Let us look at them one by one.

The leading question encourages a specific type of response from the respondent. An attempt is made to sway the respondent’s opinion of the restaurant’s service, for instance, by asking, “How would you rank the great service at our restaurant?” If the inquiry had been more objective, the respondent could find this bothersome (at best), or it might cause them to answer inappropriately.

Vague questions- As the name implies, this type of question is vague or has a lot of room for interpretation. Of course, there are occasions when open-ended inquiries are preferable since they can elicit more detailed responses from responders. But you’ll probably receive a general response if you ask a general inquiry. So, it would be best if you exercise caution.

This isn’t really of much use. Alternately, a person might go into great detail about a subject irrelevant to the inquiry. Consider your goals before deciding whether doing interviews would be a better (or extra) data collection strategy if you wanted to ask open-ended questions. Only use open-ended survey questions if they are absolutely necessary to the objectives of your study. It’s critical to keep your golden thread in mind and consider the kind of data you want to produce to ensure that your questions do not fall into one of these hazardous areas. Additionally, it’s always a good idea to perform a pilot study to evaluate your survey questions and replies to determine whether any questions are troublesome and whether the data produced is relevant.

Loaded questions without evidence to back them up to make a presumption about the respondent. For instance, it is assumed that the answer eats steak if the question asks, “Where is your favourite spot to eat steak?” This is an issue for responders who are vegetarians, vegans, or who just don’t enjoy steak.

Double-barrelled questions are a question having two (or more) different variables inside of them. In essence, it attempts to pose two queries simultaneously. As an illustration, consider:

Are peanut butter and cheese on toast your favourite food?

As you can see, this question leaves you wondering if you are being asked if they like to eat the two together on bread or if they prefer to eat one at a time. This is an issue since there are several possible answers to this question, which makes its data useless.

  1. Inappropriate response types

It’s crucial to select the correct answer type or style for each question when creating your survey. Put another way, you need to consider how respondents will enter their answers into your survey. There are, in general, three different sorts of responses.

  • Categorical response.

When answering these questions, the responder will select one of the predetermined alternatives you offer, such as gender, yes/no, ethnicity, etc.

Respondents will only have a few options to choose from when providing categorical replies, and they will only be allowed to select one. This is helpful for basic demographic information since it makes it simple to classify all possible answers.

  • Scales response

Respondents have the option to express their opinions on a scale using scales. As an illustration, you may create a 3-point scale with the choices agree, neutral, and disagree. Scales might be helpful when attempting to gauge the degree to which respondents concur with particular assertions or claims. Then, this data may be statistically examined in practical ways.

Too many or too few points on a scale might be harmful. If the only options are “strongly agree,” “neutral,” and “strongly disagree,” for instance, your respondent may choose “neutral” if they don’t feel passionate about the issue. On the other hand, if the scale has too many points, your responders may take too long to finish it and get impatient as they agonise over their responses.

  • Free from text box response

Open-ended questions were brought up before, and some drawbacks were discussed. However, this answer type has advantages because it helps perceive subtleties and finer details. An open-ended response choice, for instance, allows respondents to express their actual sentiments if they disagree with the way that some of your survey’s other questions are worded or presented.

As you can see, choosing the correct answer type is crucial since each serves a different function and has advantages and disadvantages. Make sure that every response option is suitable for the inquiry type and produces information you can meaningfully analyse.

Additionally, remember that you, the researcher, will need to analyse all of the survey’s data. As a result, you must think through how you will analyse the data from each sort of answer. Use the appropriate response type for the given question, and keep the analysis component in mind when selecting your response types.

  1. Poorly designed surveys

Although the design of each measure or scale should be carefully considered, we have only discussed the survey’s overall design. It is common to practice using Likert scales to measure theoretical notions. You must guarantee that your scales create accurate and trustworthy data if you want to measure these structures successfully.

  • Validity

If the scale accurately measures what you’re seeking to measure, it is said to be valid. However, although it can seem obvious, people frequently have different interpretations of the same questions or comments. As a result, it’s crucial to consider if the interpretations of the results of each measure are valid in light of the original construct you’re assessing and the relevant body of research.

  • Reliability

On the other hand, consistency among scales measuring the same concept is a measure of reliability (on average, of course). For example, if you have three measures evaluating employee happiness, they should correlate since they all reflect the same construct. For any specific construct, a successful survey should include numerous scales, which should “move” in unison or be “reliable.”

You must show the reliability and validity of your measurements if you’re constructing a survey. This may be accomplished in several ways utilising both statistical and non-statistical methods. We won’t go into depth about them here. Still, it’s crucial to remember that validity and reliability are essential for ensuring that your survey measures what it is intended to assess.

It’s crucial to note that there’s no need to create the wheel when creating scales for your survey. For most study topics, pre-made and tried-and-true scales are already accessible; thus, using one over creating a new scale is advised. In addition, you can frequently adapt pre-existing scales to meet your unique demands if there isn’t something currently that works for your study.

  1. Designing without consideration for analysis techniques

Naturally, you’ll want to make the best use of the survey data you collect. As a result, it’s wise to construct your survey with the analysis phase in mind from the beginning. Furthermore, the survey’s design will determine the analytic techniques you may employ for your study since it will create specific data. Therefore, you must create your survey in a way that will enable you to conduct the analyses you want to fulfil your research objectives.

Before beginning the survey design process, it’s critical to understand the statistical methodologies you want to employ clearly. Don’t be ambiguous about the precise descriptive and inferential tests you want to run. Make sure you know the presumptions behind all the statistical tests you employ and the specific kind of data (nominal, ordinal, interval, or ratio) needed for each test. You cannot start developing your survey until you have reached that clarity.

Finally, as we’ve already stressed, you must have the study’s golden thread at your mind’s forefront while developing it. Your analytical techniques will be useless if they don’t help you find the answers to your research questions. So, from the beginning, keep the overall picture and the eventual result in mind.

Let Us Recap: Survey designs mistakes.

In this article, we’ve covered several key survey design considerations and five typical blunders to avoid. These mistakes include:

  1. Poor overall structure
  2. Poorly constructed statements and questions
  3. Inappropriate response types
  4. Poorly designed surveys
  5. Designing surveys without considering the analysis techniques

Please comment below if you have any queries concerning these survey design errors. If you’d like to work one-on-one with a knowledgeable dissertation specialists here at Skylink Research, please contact us today!

Chapter 10: Quantitative analysis 101: Common Mistakes and Issues

Quantitative research is fundamentally dangerous. Though statistics do not lie, those who collect, examine, and interpret them are more than capable of occasionally fabricating information. There are many opportunities for human error to impact a quantitative study, from conception through implementation. While we have already cautioned you about the dangers of conscious and unconscious bias and finding balance in the question scope, several additional less visible traps are simple to slip into if you’re not attentive.

The five common mistakes are as follows:

  1. Not clearly defining the research question and objectives. Having a clear understanding of the goals of the study and the precise issues that need to be addressed is crucial before beginning data collection and analysis. Without a well-defined research question, it can be difficult to choose appropriate data collection and analysis methods and know what results will be considered meaningful.
  2. Collecting too much data. It can be tempting to collect as much data as possible, hoping that more information will lead to better insights. However, collecting and analysing large amounts of data can be time-consuming and expensive and may not be necessary. Instead, collecting a smaller, more targeted dataset better suited to answering the research question is often more helpful.
  3. Not considering the quality of the data. The quality of the data is just as important as the quantity. Inaccurate, irrelevant, or poorly organised data can lead to incorrect or misleading results. Therefore, when collecting data, it is crucial to consider its source, accuracy, and completeness.
  4. Analysing the data without understanding it. It is not enough to simply run statistical analyses on data; it is also essential to understand what the data represents. This entails spending adequate time carefully examining the data and considering what it could imply in light of the study topic.
  5. Not communicating the results effectively. Once the data has been analysed, it is essential to communicate the results clearly and concisely. This includes presenting the results in an appropriate format (e.g., tables, graphs, or charts) and explaining the results in plain language.

Hire a Specialist

Get Help With Your Dissertation Or Thesis, Today