Sample size calculator
How many people you need for a survey or study: Cochran's formula, Slovin's formula or a mean.
Sample size
- Sample size
- 385
- z for the confidence level
- 1.96
- Exact value
- 384.15
n₀ = z² × p(1 − p) ÷ e² = 1.96² × 0.5 × (1 − 0.5) ÷ 0.05² = 384.15
Sample size by margin of error
| Margin of error (%) | 90 % | 95 % | 99 % |
|---|---|---|---|
| ± 1 % | 6764 | 9604 | 16588 |
| ± 2 % | 1691 | 2401 | 4147 |
| ± 3 % | 752 | 1068 | 1844 |
| ± 4 % | 423 | 601 | 1037 |
| ± 5 % | 271 | 385 | 664 |
| ± 10 % | 68 | 97 | 166 |
How to use this tool
Work out a survey sample size in three steps.
Choose a method
Cochran for a proportion, Slovin's formula, or a mean with a known standard deviation.
Set the precision
Pick the confidence level and margin of error, and add the population size and expected response rate if you know them.
Read the sample
The sample size is rounded up, with the formula worked out and a table for other margins.
FAQ
How do I calculate sample size for a survey?
With Cochran's formula n₀ = z² × p(1 − p) ÷ e². At 95 % confidence (z = 1.96), a ±5 % margin and p = 50 % that gives 385 people. For a known population N, divide by 1 + (n₀ − 1) ÷ N.
What is Slovin's formula?
n = N ÷ (1 + N × e²), with N the population and e the margin of error. For N = 1,000 and e = 5 % it gives 286. It assumes p = 50 % and ignores the confidence level, so many statisticians prefer Cochran's formula.
Why use 50 % as the expected proportion?
p(1 − p) is largest at 50 %, so it gives the safest (largest) sample when you do not know the answer in advance. If an earlier study found 20 %, using it gives a smaller sample.
What is the finite population correction?
When the sample is a noticeable share of a small population, fewer people are needed. Enter the population size and the calculator applies n = n₀ ÷ (1 + (n₀ − 1) ÷ N).
How many people should I invite?
Divide the sample size by the share you expect to answer. With 385 needed and a 40 % response rate, invite 963. Enter the response rate to see it.