A research question you can actually answer
The difference between a topic and a question, and why the question decides everything that follows.
A topic is 'diabetes in the elderly'. A research question is 'Does a twelve-week supervised walking programme reduce HbA1c in adults over 60 with type 2 diabetes, compared with usual advice?' The second names who you will study, what you will do to them or observe about them, what you will measure, and what you will compare it against.
Why it matters
Every later decision follows from the question. It fixes your study design, your variables, your sample size and the statistical test that applies. A vague question cannot be analysed, because there is nothing definite to test. Most dissertations that go wrong went wrong here, months before anyone noticed.
An example
Weak: 'A study on physiotherapy in knee osteoarthritis.'
Better: 'In adults aged 45–70 with radiographically confirmed knee osteoarthritis, does a twelve-week supervised exercise programme reduce pain on the Visual Analogue Scale more than a home exercise programme?'
The second version already tells you the design (two groups, before and after), the outcome (VAS pain, a numerical measure), and therefore the analysis.
Common mistakes
- Asking two questions at once — split them into separate objectives.
- Naming an outcome you cannot measure with what you have access to.
- Leaving the comparison group unstated. 'Does X work?' is not answerable; 'better than what?' is.
Read next
- Objectives, and why your results are organised by them — One objective, one analysis, one paragraph of results.
- Which study design you are actually running — Observational or interventional; and if observational, which direction time runs in.
Chavery Research Companion applies this to your own study: it asks the questions in plain language, checks the assumptions against your data, recommends the test, and writes the sentence that reports it. Start free — planning and the master chart cost nothing.