Skip to content

Free Sample Size Calculator

How many survey responses you need for a confidence level. Completely free, with no sign-up and no upload.

  • 100% free
  • No sign-up
  • No watermark
  • Works in your browser

Also called: survey sample size calculator, sample size for proportions, margin of error calculator, sample size formula.

About Sample Size Calculator

Work out how many survey responses you need for a chosen confidence level and margin of error, using Cochran's formula with a finite-population correction. Students, researchers and marketers can plan surveys in seconds and see the Z-score behind the answer.

How to use Sample Size Calculator

  1. Pick a confidence level (95% is standard).
  2. Set the margin of error you can accept.
  3. Optionally enter your population size.

Tips and good to know

  • Use 50% expected proportion if you don't know it; it's the safest.
  • Halving the margin of error roughly quadruples the sample.
  • Small populations need fewer responses.

What drives sample size

Three choices set the size of a survey sample: the confidence level (usually 95%), the margin of error (for example ±5%) and the expected proportion, with 50% as the safe assumption because it needs the most responses. At 95% confidence and ±5% margin, about 385 responses are enough for a very large population; halving the margin to ±2.5% roughly quadruples the sample to about 1,537.

For small populations, a finite population correction reduces the number needed. Remember that sample size controls random error only: a biased sample, such as only surveying your own followers, gives misleading results however large it is. Plan for non-responses by inviting more people than the target.

Confidence level and margin of error

A 95% confidence level with a ±5% margin of error means that if you repeated the survey many times, about 95% of results would fall within five points of the true value. For a large population, that needs about 385 responses. Halving the margin to ±2.5% roughly quadruples the sample needed.

Population size matters less than people expect: once it is in the thousands, the required sample barely grows. What matters more is who answers. A large sample of self-selected respondents can still be biased, so random selection and good response rates are as important as the number.

Frequently asked questions

Why 385?

At 95% confidence and ±5% margin, a large population needs 385 responses.

Is anything uploaded?

No. Everything runs in your browser on your device; nothing is uploaded.

Is Sample Size Calculator free?

Yes. Sample Size Calculator is 100% free: no sign-up, no paid plan, no trial and no limit on how often you use it. It runs in your browser, and ToolzAura is paid for by ads, so every tool stays free.

Are my files uploaded?

No. This tool runs in your browser, so your input stays on your device.

Maintained by Malik Shaheer · Last reviewed · How we test tools · Report a problem

Related tools

Scientific Calculator

Trigonometry, logs, powers and brackets.

Calculators

Speed Distance Time Calculator

Solve for any one of speed, distance or time.

Calculators

Statistics Calculator

Mean, variance, standard deviation and more.

Calculators

Time Calculator

Add and subtract hours, minutes and seconds.

Calculators

Triangle Calculator

Solve right triangles (Pythagoras) or any triangle from 3 sides.

Calculators

Unit Price Calculator

Compare price per kg, litre or item to find the best deal.

Calculators