Skip to main content

Sample Size Calculator

Calculate the required sample size for surveys and statistical studies. Determine how many responses you need for statistically reliable results.

Sample Size Calculator

Calculate the required sample size for surveys and statistical studies

Higher confidence requires larger sample sizes

Smaller margin of error requires larger sample sizes

Use 50% if unknown (gives maximum sample size)

Formula

n = (Z² × p × (1-p)) / E²

Where Z = Z-score for confidence level, p = expected proportion, E = margin of error. For finite populations, apply correction: n_adj = n / (1 + (n-1)/N)

Sample Size Guidelines

Population Size±3% Error±5% Error±10% Error
100928049
50034121781
1,00051627888
10,00096437095
100,000+1,06738396

* Based on 95% confidence level and 50% expected proportion

How to Use

  1. 1
    Select confidence levelChoose your desired confidence level (90%, 95%, or 99%).
  2. 2
    Set margin of errorSelect the acceptable margin of error for your survey results.
  3. 3
    Enter expected proportionEstimate the expected response proportion (use 50% if unknown).
  4. 4
    Add population sizeOptionally enter your total population size for finite population correction.
  5. 5
    View resultsSee the required sample size for your survey.

Frequently Asked Questions

What is sample size?

Sample size is the number of observations or responses needed in a survey or study to achieve statistically reliable results. A larger sample size generally provides more accurate estimates.

What is margin of error?

Margin of error indicates the range within which the true population value is likely to fall. A ±5% margin of error means your results could be 5 percentage points higher or lower than the true value.

What confidence level should I use?

95% is the most commonly used confidence level in research. Use 99% for critical decisions requiring higher certainty, or 90% when resources are limited and some uncertainty is acceptable.

Why does population size matter?

For small populations, you can survey a smaller percentage and still get reliable results. The finite population correction reduces the required sample size when your population is known and limited.

What if I don't know the expected proportion?

Use 50% as the expected proportion. This gives the maximum (most conservative) sample size, ensuring your results will be reliable regardless of the actual proportion.