Sample Size Calculator

About this calculator

Deciding how many people to survey is a genuine statistical problem, not a guess: too few respondents and your results carry too much uncertainty to trust, too many and you're wasting time and budget collecting data you didn't need. This calculator applies Cochran's formula, n = Z² × p(1−p) ÷ E², to find the minimum sample size needed for a target confidence level (how sure you want to be that your results reflect the true population) and margin of error (how much wiggle room you're willing to accept), using the most conservative assumed response split of 50/50 unless you specify a different expected proportion. When you provide a known population size, it applies a finite-population correction that shrinks the estimate, since surveying a large share of a small population needs proportionally fewer respondents than the base formula assumes. That replaces guesswork or rules of thumb with the actual statistical formula behind reliable survey design.

How to use this

1. 1Enter your desired confidence level, commonly 95%.
2. 2Enter your acceptable margin of error, commonly 5%.
3. 3Optionally enter your total population size if it's known and finite, then read the required sample size.

Troubleshooting

• The sample size seems too large for my project's budget.

  Sample size grows quickly as margin of error shrinks, since error is squared in the formula's denominator. Accepting a slightly larger margin of error (say 7% instead of 5%) often reduces the required sample size substantially.

• Do I need to know my population size?

  No, leaving it blank calculates the sample size for an effectively infinite population, a reasonable default for large or unknown populations, entering a known finite population size will typically reduce the required sample size slightly.

Frequently asked questions