Survey Sample Size Calculator

How the sample size calculation works

The calculator estimates a sample for a population proportion, then applies a finite population correction. A 50/50 expected split is the conservative default because it produces the highest required sample size.

The result is the number of completed responses, not invitations. If you expect a 20% response rate and need 377 completes, plan to invite roughly 1,885 eligible people.

Choose realistic research settings

• Use 95% confidence and ±5% margin of error as a common planning starting point, then tighten the margin only when the decision justifies the extra responses.
• Use the addressable population for the decision, such as active customers in a market, not every visitor your store has ever had.
• If you will compare customer segments, each segment needs enough responses for the precision you want within that segment.

What this calculator does not prove

A large sample does not remove selection bias, non-response bias, leading questions, or poor timing. Statistical precision matters only after the people who respond reasonably represent the population you want to understand.