Sample Size Calculator
Required Sample Size
—
Confidence Z-Score
—
With Finite Population Correction
—
How to Determine Sample Size
Sample size calculation determines how many responses you need for your survey or study to produce statistically reliable results. This calculator uses Cochran's formula: n = Z^2 * p * (1-p) / e^2, where Z is the Z-score for your confidence level, p is the expected proportion, and e is the margin of error.
A 95% confidence level with 5% margin of error is the most common standard, requiring about 385 responses for a large population. Higher confidence or smaller margins of error require larger samples. If your population is small (under 10,000), the finite population correction reduces the required sample size.
Use 50% as the expected proportion when you are unsure — this produces the most conservative (largest) sample size estimate. If you have reason to expect the true proportion is far from 50% (like 10% or 90%), a smaller sample may suffice. Always plan to collect 10-20% more responses than the minimum to account for incomplete surveys.
Frequently Asked Questions
What is a good sample size for a survey?
For most surveys with a large population, 385 responses give 95% confidence with 5% margin of error. For smaller populations, you may need fewer. For academic research, 1,000+ responses are often preferred.
What does margin of error mean?
If your survey finds 60% support with a 5% margin of error, the true population value is likely between 55% and 65%. Smaller margins of error require larger samples but give more precise results.
What confidence level should I use?
95% is the standard for most research and business surveys. Academic research often uses 99%. Preliminary or exploratory research may use 90%. Higher confidence requires larger samples.
Does population size matter for sample size?
For populations over 10,000, population size has minimal effect on required sample size. For smaller populations, the finite population correction significantly reduces the required sample. A town of 500 people needs far fewer responses than a national survey.