Free Dissertation Sample Size Calculator
Estimate how many responses you need for a survey-based dissertation. Set your confidence level, margin of error and population, then use the result to plan recruitment and justify your sample.
- Free to use
- Runs in your browser
- Made for survey research
Cochran's formula with optional finite population correction, for survey-based dissertations.
How to use the sample size calculator
Supervisors and examiners expect you to justify your sample. A calculated figure is far more convincing than a number chosen because it felt about right.
- Estimate your populationThis is the total group you want to draw conclusions about. If it is very large or unknown, use a large figure.
- Choose a confidence level95 per cent is the most common choice in student research.
- Set a margin of errorFive per cent is typical. Smaller margins need more responses.
- Record the inputsReport the settings as well as the result, because your methodology should show both.
How each input changes your sample size
Understanding the trade-offs helps you defend your choices.
| Setting | Typical value | Effect on sample size |
|---|---|---|
| Confidence level | 90, 95 or 99 per cent | Higher confidence needs a larger sample |
| Margin of error | Five per cent is common | A smaller margin needs a larger sample |
| Population size | The total group you study | Matters mostly for small populations. Beyond several thousand, the figure barely changes |
| Expected proportion | 50 per cent when unknown | 50 per cent gives the most cautious, largest estimate |
Worked example. For a very large population, 95 per cent confidence, a five per cent margin of error and a 50 per cent expected proportion, the standard survey formula gives about 385 responses. Results can differ slightly depending on rounding.
When a sample size calculator is not the right tool
Qualitative research
Interview and focus group studies justify samples through purposive sampling and ideas such as data saturation, not formulas.
Hypothesis tests
If you plan a t-test, ANOVA or regression, a power analysis is usually more appropriate. Free software such as G*Power can help.
Response rates
The result is the number of completed responses you need. Invite more people, because not everyone replies.
Convenience samples
A calculated size does not make a convenience sample representative. Acknowledge this as a limitation.
Report it properly. State the confidence level, margin of error, population and calculated figure in your methodology. Then report your achieved sample and discuss any shortfall.
Sample size calculator FAQs
Is the sample size calculator free?
Yes. The tool is free to use and you do not need to pay to estimate your sample.
What sample size is enough for an undergraduate dissertation?
There is no universal number. It depends on your design, population and department guidance, so agree a realistic target with your supervisor.
What if I cannot reach the calculated sample?
This is common. Report your achieved sample honestly, explain the effect on precision and discuss it as a limitation. Raise concerns with your supervisor early.
Does population size matter?
It matters mainly when the population is small. For large populations, the required sample changes very little as the population grows.
Can I use it for interviews?
No. Interview samples are justified by your aims and the depth of information needed, not by a survey formula.
Planning your method?
Sample size is one part of your design. Read our advice on dissertation methodology, choose an analysis with the statistical test selector, or map your data collection with the dissertation timeline planner.
Get Dissertation Support