Sample size calculator

You need 385 respondents

If one in five responds, send the invitation to ~1,925 people

Recruiting tools: the “Recruiting and panels” station

In plain words

Example: you surveyed 385 people and 40% said “yes”. If you had asked everyone, between 35% and 45% would say “yes” — with 95 in 100 confidence.
Confidence level is how sure you are that the true answer falls in the range: 95% means “in 95 cases out of 100”.
Margin of error (confidence interval) is how many percent the survey result may differ from the answer of all people.
Population is everyone you want to learn about.
Expected proportion is the share of answers you expect; 50% gives the most reliable sample.

How it is calculated

n0 = Z² · p · (1 − p) / e²

n = n0 / (1 + (n0 − 1) / N)

Cochran’s formula with the finite population correction. Z is the confidence coefficient (1.645 / 1.96 / 2.576), p is the expected proportion, e is the margin of error. The unrounded n0 goes into the correction; the result is rounded up.

Survey tools

Questions and answers

How many respondents do I need for a survey?

For a large population at 95% confidence and ±5% margin of error you need 385 respondents. A smaller margin needs a bigger sample: ±3% requires 1068.

Do I need to know the population size?

No. If the population is large or unknown, leave the field empty. The correction only matters for small groups, such as employees of one company.