How to Evaluate the Feasibility of a Research Idea
Feasibility means that you can answer the question with the data, time, skills and approvals you actually have. Checking it early, with a short checklist, prevents projects from stalling halfway.
Feasibility checklist
| Domain | Questions |
|---|---|
| Data | Do the data exist? Who owns them? Are the key variables recorded consistently? |
| Sample | Are there enough eligible patients or records for a meaningful estimate? |
| Time | How long will approvals, data collection and analysis take? |
| Skills | Who can do searching, data handling, statistics? |
| Ethics and access | Is ethics review needed? Is data access permitted? |
| Supervision | Does an experienced person agree to supervise? |
| Resources | Software, storage, costs, publication fees? |
A quick way to test
- List the variables you need and mark where each will come from.
- Count eligible cases in a small pilot (for example 20 records).
- Estimate the proportion with missing key data.
- Draft a timeline with realistic approvals.
Illustrative example
Invented for teaching. A student wants to study sepsis outcomes. In a pilot of 20 charts, 12 lack the timing of the first antibiotic dose. The primary variable is missing in 60% of records, so the study as planned is not feasible. She changes the question to what is recorded reliably, or plans a prospective data form.
Estimating sample feasibility
A rough feasibility count helps: if you need to compare two groups and your pilot shows that only 10 eligible patients per year have the condition, a three-month study cannot work. Ask a statistician whether your expected sample can detect an effect of a meaningful size; if not, consider a descriptive design, a pilot study, or a larger collaboration. A feasibility or pilot study is itself a valid project; see What Is a Pilot Study?.
Common pitfalls
- Assuming data are available and complete.
- Underestimating approval time.
- Counting on one busy supervisor with no backup.
Key takeaways
- Test feasibility with a small pilot before writing the full protocol.
- If a key variable is unreliable, change the question, not the data.
References and further reading
- Hulley SB, Cummings SR, Browner WS, Grady D, Newman TB. Designing Clinical Research. 4th ed. Lippincott Williams & Wilkins; 2013. Link
- Chan AW, Tetzlaff JM, Altman DG, et al. SPIRIT 2013 statement: defining standard protocol items for clinical trials. Ann Intern Med. 2013;158(3):200-207. doi:10.7326/0003-4819-158-3-201301080-00007
Related reading
This page is general educational information about research methods. It is not medical, legal or regulatory advice; follow your institution's ethics board and your target journal's instructions.