Sample Size Calculator

Sample size = (Z² × p × (1−p)) ÷ E², where Z is the z-score for your confidence level, p is the expected proportion (0.5 is the most conservative, giving the largest required sample), and E is your margin of error as a decimal. If you know your total population size, a finite population correction reduces this further.

95% confidence with a 5% margin of error is the most common standard for general surveys — it's the source of the widely-cited '385 responses' rule of thumb for very large or unknown populations. Higher confidence (99%) or a tighter margin of error (e.g., 3%) requires a larger sample.

When you're surveying a limited, known population (like all 2,000 employees at a company, not a large general population), the sample size needed is smaller than for an infinite population — entering your population size applies this correction automatically.

Use 0.5 (50%) — it's the most conservative assumption, since p×(1−p) is at its maximum at p=0.5, and using it guarantees your sample size is large enough regardless of how the responses actually split.