Sample Size Calculator
A free online sample size calculator for your thesis or dissertation survey. Get your minimum sample size in one click, then paste the sentence into your methodology chapter.
Calculate your sample size
Who it's for: Students whose advisor said "make sure your sample is big enough" and who need a survey sample size calculator that shows its working, not just a number.
What you get
- The minimum number of completed responses your survey needs, instead of a rule of thumb like "a few hundred"
- A sentence for your methodology chapter that states the formula and the settings behind your number
- A smaller number when your population is small and known, using the finite population correction
How it works
- Pick your confidence level and margin of error. 95% and 5% are the defaults, and if your advisor or program asks for 99% or 3%, change them and the number updates
- Add your population size if you know it. A population of 100 needs 80 responses, 1,000 needs 278, and a very large population needs 385
- Read the result as completed responses, not invitations. Divide it by the response rate you expect to know how many people to invite
How to calculate sample size
A number that comes from "a few hundred" is hard to defend in front of a committee. A number that comes from a formula isn't. The calculator uses Cochran's formula: n = z² × p × (1 − p) ÷ e². Here z is the z-score for your confidence level (1.96 for 95%), p is the share you expect to answer a particular way (50% if you have no earlier estimate, because it gives the safest, largest sample), and e is your margin of error as a decimal.
For 95% confidence and a 5% margin of error, 1.96² × 0.5 × 0.5 ÷ 0.05² = 384.16, which rounds up to a required sample size of 385. With a known population, the finite population correction n = n0 ÷ (1 + (n0 − 1) ÷ N) brings it down to 278 for a population of 1,000. The margin of error is the plus-or-minus around your result, which is half the width of the confidence interval.
Once your sample is planned, organize your reading with the free Literature Review Tracker.
Common questions
What sample size do I need for a thesis or dissertation survey?
For a large population, a 95% confidence level and a 5% margin of error need 385 responses. A 99% confidence level needs 664, and a 90% confidence level needs 271. For a population of 100 the minimum sample size is 80, and for 1,000 it is 278. Ask your advisor which confidence level and margin of error your program expects.
What is a statistically significant sample size?
There is no single number. Statistical significance depends on the effect you want to detect and the power of your test, not on sample size alone. This calculator gives the sample needed to estimate a percentage within a chosen margin of error. To compare groups, for example with a t-test, you need a power analysis.
Does population size matter?
Only when the sample would be a large share of a small population. Once a population reaches the tens of thousands, the required sample barely changes: 370 for 10,000 and 383 for 100,000 at 95% confidence and a 5% margin of error.
Why use 50% as the expected proportion?
50% gives the largest sample size, so it is the safe choice when you have no earlier estimate. If you know the true proportion is nearer 10% or 90%, enter it under the expected proportion option for a smaller sample.
How many people should I invite if not everyone responds?
Divide the sample size by your expected response rate. If you need 385 responses and expect 25% to reply, invite about 1,540 people.
Still planning your thesis?
Organize your sources by theme and method before you build your argument.
Get the Literature Review Tracker →Want more? More free templates · Journal