Skip to content

Sample Size Calculator

Work out how many people to survey, or how precise your survey is.

%
%

Use 50% if unsure (gives the largest, safest sample).

Leave empty for a very large or unknown population.

Sample size needed

385

for ±5% at 95% confidence

Unrounded sample size
384.1459
Z-score
1.959964
Sample size for an unlimited population
385

How it was calculated

  1. z for 95% confidence = 1.959964
  2. n₀ = z² × p(1 - p) / E²
  3. n₀ = 1.959964² × 0.5 × 0.5 / 0.05² = 384.145882
  4. Round up: n = 385

Calculations run on this device and your inputs are not uploaded. A share link puts your inputs in the URL, so anyone with the link can read them.

More Math Calculators

All calculators

How the sample size calculator works

The sample size tells you how many responses you need so that your survey result is within a chosen margin of error of the true value, at a chosen confidence level. The formula is n = z² × p(1 - p) / E², where z comes from the confidence level (1.96 for 95%), p is the expected proportion and E is the margin of error.

If you don't know the proportion, use 50%: it gives the largest sample and so the safest answer. For a small population of known size N, the finite population correction n / (1 + (n - 1) / N) reduces the sample you need.

The margin of error tab reverses the formula: E = z × √(p(1 - p) / n). These formulas assume a simple random sample; real surveys with low response rates or clustered samples need more.

Using and checking your result

Published by JustYourCalculator. Check the units and assumptions above, and compare a known example before relying on the output. Calculations use browser arithmetic and may round displayed values.

Share links may contain your input values. Anyone with the URL can read them; avoid sharing sensitive personal or financial information.

Frequently asked questions

At 95% confidence (z = 1.96), a 5% margin of error and p = 50%, n = 1.96² × 0.25 / 0.05² = 384.16, which rounds up to 385.

Only when the sample is a noticeable share of the population. For a city or a country, 385 is enough for ±5%; for a company of 500 people, you need about 218.

Survey more people. Halving the margin of error needs about four times the sample, because E shrinks with the square root of n.

Yes. Every calculator is free with no sign-up. Clearly labeled ads keep it that way.

Calculations run in your browser. Share links put inputs in the URL, which can be read by anyone you send it to and is sent to the hosting server when opened. Avoid sharing sensitive numbers. Currency conversion requests public exchange rates.

Results follow the formulas and assumptions shown, with normal rounding and numerical limits. Taxes, rates and health guidance can change, so treat these as estimates and confirm important decisions with a qualified professional.