Guide · Evidence Notes
Choose a research method by question, evidence and constraints
Methods follow questions. Decide what your question asks, what data you can actually reach and whether you can influence who receives what, and the choice narrows quickly.
Practice 11: Research supervision, academic coaching & publication support
The short answer
Match the design to the question. How much or how many: a survey. What is associated with what: analysis of survey or existing data. Whether something caused an effect: an experiment, or a quasi-experimental comparison. How people experience something: interviews or case studies. What works, for whom and in what conditions: realist evaluation or mixed methods. Then test the design against your data, sample and time.
Start from the question
Each kind of question needs a different kind of evidence. A survey can estimate how common something is; it cannot explain why people act as they do. Interviews can explain; they cannot estimate a proportion.
Can you decide who gets the intervention?
If you can assign it at random, a randomised trial may be possible. If you cannot, quasi-experimental designs compare groups instead, and their conclusions rest on stated assumptions, above all that the comparison group would have changed in the same way.
Data, numbers and time
The data you can reach limits the design. Quantitative questions with fewer than about a hundred participants deserve a sample-size or power calculation before you commit, and fieldwork and ethics approval always take longer than planned.
A worked example
In the worked example in the research methodology decision aid, a question about what is associated with loan repayment, with a survey, an existing dataset and about 250 participants, points to a cross-sectional survey or analysis of existing data. The aid states the assumption that matters, that associations are not causes and confounders must be measured, and the analysis to learn: correlation, regression and handling missing data. Adding interviews would open an explanatory mixed-methods design.
Who decides
Your supervisor and ethics committee judge whether a design fits your question. The analysis is learned and done by the researcher; see academic integrity.
What this guide does not cover
The aid explains options; it does not choose or approve a design. Discipline norms vary, and your supervisor has the final word.
Responsible for this guide
Examples in this guide are illustrative, not client results. Figures come from the free tool’s worked example; change the inputs in the tool to see your own.
Related services
The same method, delivered with you: scoped in writing, with a named principal and a fee agreed before any work begins.
Research methods and statistics support
Help with research design, quantitative and qualitative methods and statistics, so you understand and can defend every choice. The analysis is yours, and the assistance is declared.
See the serviceServiceResearch-methods bootcamps and supervisor training
Practical bootcamps for doctoral schools, universities and professional bodies, and training that helps supervisors guide researchers well, with outcomes assessed.
See the serviceMore from Evidence Notes
What needs to move forward?
Tell us the decision, the challenge or the opportunity. We reply with a scoped approach, a named principal and a fee before any work begins.
No charge to submit an enquiry.