The format of a PhD thesis proposal varies from one institution to another. In most cases, however, chapter 3 of the PhD thesis is the research methodology chapter.
This article discusses the main sections of the research methodology chapter and provides tips on how best to write it.
- Introduction
- Research design
- Population and sampling
- Random sampling
- Non-random sampling
- Data collection methods and tools
- Questionnaires
- Interviews
- Focus group discussions
- Observation
- Document review
- Ethical considerations
- Data analysis
- Limitations of the study
- Final thoughts on how to write chapter 3 of a PhD thesis proposal
Introduction
The first section is a brief introduction to the chapter, which highlights what the chapter is about.
Research design
This section discusses the research design that the study will use. The research design should be guided by the research objectives and research questions the student wants to answer. The research design can be: quantitative, qualitative, or mixed-methods design.
In quantitative research, the study will collect, analyse and present numerical data in the form of statistics. The statistics can be descriptive, inferential, or a mix of both.
In qualitative research, the study collects, analyses and presents data that is in the form of words, opinions, or thoughts of the respondents. Its focus is on the lived-in experiences of the respondents with regard to the problem under investigation.
In mixed-methods research, the study uses a combination of quantitative and qualitative research methods. So some of the research questions render themselves to quantitative research, while others to qualitative research.
Each of these research designs has its pros and cons.
Population and sampling
Population of study refers to the entire list of your subjects of interest. If the population is so small, the student can opt to include all the subjects in the study. However, if the population is large, it becomes difficult – both time-wise and resource-wise – to include all the subjects in the study.
A sample is a sub-set of the population of study from which data will be collected to enable the student understand the population.
An example of population vs. sample: Suppose a study aims at investigating the effects of COVID-19 pandemic on micro and small enterprises (MSEs) in Kenya. The population of the study will be all the MSEs in Kenya, which are thousands in number, distributed across the country. It will be impossible for the student to collect data from all those MSEs and therefore a sample will be necessary. The sample size the student decides to use will depend on whether the study is quantitative, qualitative or both. For quantitative studies, a large sample size is necessary, while for qualitative study, the sample size need not be large.
Sampling is the process by which a sample is drawn from a population. There are two categories of sampling techniques, namely: random and non-random sampling. The use of either depends on your research design.
Random sampling
In random sampling, the sample is selected randomly and each subject in the population has an equal chance of being selected for the sample.
The advantage of random sampling is that the results from the sample can be generalised to the population, especially if the sample size is sufficiently large.
Random sampling is used primarily for quantitative studies.
Non-random sampling
In non-random sampling, the sample is selected deliberately rather than randomly. As a result, the subjects do not have an equal chance of being selected for the sample.
It is also referred to as purposive sampling, meaning that the sample being selected have a specific purpose.
Non-random sampling is used primarily for qualitative sampling.
Data collection methods and tools
In this section, the student is expected to discuss in detail the type of data he will collect, that is, whether primary or secondary data (or both) and how he will go about collecting the data from the sample. The methods and tools used also depend on the research design. They include:
Questionnaires
Questionnaires are mostly used to collect quantitative data.
Questionnaires are structured in nature and include closed-ended questions.
There are four main types of closed-ended questions used in questionnaires:
- Numerical questions:
- for example: how many children do you have?
- Two-option response questions:
- for example: does your household have a radio? 1. Yes 2. No
- Multiple choice questions:
- for example: what is your highest level of education? 1. No education 2. Primary education 3. Secondary education 4. Tertiary level
- Likert scale or rating questions:
- for example: please rate your level of satisfaction with the water services board. 1. Very dissatisfied 2. Dissatisfied 3. Neutral 4. Satisfied 5. Very satisfied
There are two forms of questionnaaire delivery: facilitated questionnaires and self-administered questionnaires.
For facilitated questionnaires, the researcher administers the questionnaire while in self-administered questionnaires, the respondent fills in the questionnaire without the presence of the researcher.
Self-administered questionnaires can be delivered by hand, or mailed via the post office or through email. Facilitated questionnaires can be done either face-to-face or through telephone. Each of these options has its pros and cons.
Interviews
Interviews are oral discussions between the researcher and the respondent.
Unlike questionnaires, interviews are semi-structured. The researcher uses an interview guide to guide the discussion. The interview guide has some questions that the researcher asks the respondent. However, subsequent questions and discussions are determined by the responses given by the respondent to previous questions.
The flow of interviews will therefore vary from one respondent to another depending on their personalities and openness to responding to the questions.
Focus group discussions
Whereas interviews are held with individuals, focus group discussions (FGDs) are held with a group of respondents who are key to the problem under investigation.
The participants for an FGD should be selected carefully to represent diverse subjects of the population under investigation.
In the example of the study on the effects of COVID-19 pandemic on micro and small enterprises in Kenya, the student can create a focus group that has the following members: a female-owned enterprise, a male-owned enterprise, a youth-owned enterprise, a family-run enterprise, a non-family-run enterprise, customers of the enterprises, and an employee of the Micro and Small Enterprises Authority (MSEA). Such a focus group would have rich discussions of the views of the different players in the industry.
Observation
Observation is also a method of data collection that is commonly used. There are two types of observation: participant observation and non-participant observation.
In participant observation, the researcher immerses himself into the environment of study. In the MSEs study, for example, the researcher would choose to work in one of the enterprises for a period of time where he would observe how the business performs on a day-to-day basis.
In non-participant observation, the researcher removes himself from the environment of study and instead observes from a distance. In the MSEs study, for example, the researcher would go somewhere close to an enterprise and observe how the business performs e.g. how many clients visit the business on a day-to-day basis.
Each observation type has its own pros and cons.
During observation, the researcher should use an observation checklist that guides him on what needs to be observed and the frequency of observation.
Document review
In this data collection methods, the student obtains relevant documents to his study and reviews them in-depth. For instance, in the MSEs, the student can review the MSEs Policy of Kenya, Strategic Plan of the Micro and Small Enterprises Authority etc. Such documents are useful in informing the researcher the current state of affairs of the problem under investigation.
Ethical considerations
This section highlights the ethical considerations that would be followed during the data collection process. The ethical considerations vary from study to study and include:
Consent: the researcher should seek informed consent from the respondent before the data collection begins. For instance, when administering the questionnaire or conducting interviews, the researcher should start by informing the respondent what the study is about, how the respondent was selected, and the benefits of the study and then seek permission to continue with the study. The consent can be in written or oral form.
Compensation for participation: while participating in the study should be voluntary, some research have allowance for monetary compensation. The respondents should be informed of any plans to compensate them but after they have participated in the study, not before.
Confidentiality: the researcher should assure the respondents that their responses will be kept confidential.
Dissemination of the study findings with the respondents: there should be a plan for the student to disseminate the results of the study with the participants, for instance, through validation workshops or written publications.
Additionally, most academic institutions require their students to obtain ethical clearance for their research from the relevant authorities. Students should check if this requirement applies to them and follow the necessary procedure.
Data analysis
In this section, the student should discuss how the data collected will be analysed. Data analysis methods and techniques vary depending on whether the data is quantitative or qualitative.
For quantitative research, the interest of data analysis is the numbers which can be obtained through descriptive statistics and inferential statistics.
Descriptive statistics is usually the first step in analysing quantitative data. There are three categories of descriptive statistics:
- Measures of frequency: frequency table or cross-tabulation table.
- Measures of central tendency: mean, median and mode.
- Measures of variability: range, standard deviation and variance.
Inferential analysis goes a step further and looks at whether the results from the sample can be generalised to the wider population. For studies that involve interventions, inferential analysis is used to check if the intervention has any impact on the population in which it was implemented.
Some inferential analysis techniques include:
- Checking for differences between groups: t-test, analysis of variance (ANOVA) and Chi-square test.
- Checking for correlation or causation between variables: linear regression, logistic regression (logit, probit, multinomial logit/probit models etc).
The choice of data analysis technique will depend on the type of data the student has. For instance, a dependent variable that is continuous will use a different analysis technique from a dependent variable that is categorical in nature. Additionally, the choice of the data analysis technique should be guided by the research questions. The results from the analysis should be able to provide answers to the research questions posed.
For qualitative research, data analysis involves analysing the content of the interviews and focus group discussions. The content can be in different forms such as interview recordings and hand-written notes.
The recordings should be transcribed first and the notes should be organised well before analysis can take place.
The analysis of qualitative data involves coding the data, indexing the data and framing the data to identify the themes that emerge from the data.
Besides discussing the data analysis techniques, the student should discuss the softwares that will be used for analysis. There are many softwares in the market that are used for quantitative (such as SPSS and STATA) and qualitative data (such as NVivo).
Limitations of the study
The last section in the research methodology chapter discusses the potential limitations of the study and how the limitations will be mitigated. An example of study limitation is low response rate of questionnaires, which can be mitigated through triangulation.
The limitations of the study will vary from one study to another and depend on the context within which the study is conducted.
Final thoughts on how to write chapter 3 of a PhD thesis proposal
This article provided a detailed guide on how to write the research methodology chapter of a PhD thesis proposal. The research methodology chapter is informed by the research problem and research questions specified in chapter 1 of the thesis proposal. Students should therefore think through carefully their research study from the beginning because what is in the introduction chapter informs the content in the remaining chapters of the proposal and final thesis.
Related posts
How To Write Chapter 1 Of A PhD Thesis Proposal (A Practical Guide)
How To Write Chapter 2 Of A PhD Thesis Proposal (A Beginner’s Guide)