New: a free Sample Size Calculator for surveys — try it now →
Services Free Tools Resources Insights About AI tools & deals Thesis help by country Book a free call How to pay Refer & earn For brands & sponsors Contact Chat on WhatsApp
  1. Home
  2. Free research tools
  3. Sample size calculator
Free tool

Sample Size Calculator for Surveys

Enter your confidence level, margin of error and (if you know it) your population size. The calculator shows the sample size and the exact working, ready for your methodology chapter.

385completed responses needed

Show the working

Runs entirely in your browser — nothing you type is sent or stored.

How the calculation works

For estimating a proportion, the minimum sample size for a large population is:

n₀ = z² × p(1 − p) ÷ e²

  • z is the z-score for your confidence level: 1.645 (90%), 1.96 (95%) or 2.576 (99%)
  • p is the expected proportion. Use 50% when you do not know it — it gives the largest, safest sample
  • e is the margin of error as a decimal (5% = 0.05)

If your population is a known, limited group, the finite population correction reduces the number:

n = n₀ ÷ (1 + (n₀ − 1) ÷ N)

How to report it

A typical sentence for your methodology chapter: "Using a 95% confidence level, a 5% margin of error and an expected proportion of 50%, the minimum required sample was 385 (Cochran, 1977)." Add the finite population correction if you used it.

Limits to keep in mind

This formula is for estimating proportions in simple random samples. Regression, structural equation modelling and experiments are usually planned with a power analysis instead, and you should always inflate the target for the response rate you expect.

Questions

Why do so many studies use 385 respondents?

Because 385 is the result for 95% confidence, a 5% margin of error and p = 50% in a large population. It only applies when those are your assumptions.

What if I do not know my population size?

Leave it empty. For populations above roughly 20,000 the correction makes almost no difference.

Should I use 50% for the expected proportion?

Use 50% unless earlier studies give a reliable estimate. It produces the largest sample, so it is the cautious choice.

Chat on WhatsApp