Find the exact number of survey responses you need
Survey Parameters
Use 50% if unknown — gives largest (safest) sample.
Enables finite population correction for smaller groups.
Results
Formula used
n = (Z² × p × (1 − p)) / e²
n_adj = n / (1 + (n − 1) / N) ← finite pop. correction
Where Z = 1.9600 (z-score for 95% confidence), p = 0.50 (proportion), e = 0.05 (margin of error), N = 10,000 (population).
Common Z-Scores
Key Concepts
Determine exactly how many survey responses you need with this free sample size calculator. Enter your desired confidence level (typically 95%), margin of error (±5%), and population size to instantly compute a statistically valid sample using Cochran's formula with finite population correction. Whether you're running a market research survey, academic study, or quality audit, get the right number in seconds.
95% is the standard for most research and surveys — it means you can be 95% certain the true population value falls within your margin of error. Use 99% for critical decisions (medical, financial) where higher certainty is worth a larger sample, or 90% for exploratory studies where speed matters more than precision.
Proportion (p) is your best estimate of the percentage of people who will answer 'yes' to your key question. It affects how variable responses will be. If unknown, always use 50% — this is the most conservative assumption and produces the largest (safest) sample size, guaranteeing your results are valid regardless of the true proportion.
Enter your population size when surveying a defined, countable group — such as employees at a company, students in a school, or customers on a list. The calculator applies a finite population correction that reduces the required sample size, sometimes significantly. Leave it blank when surveying the general public or any large, effectively unlimited population.
Margin of error (±%) defines the maximum expected difference between your sample result and the true population value. A ±5% margin is standard for general surveys. Smaller margins (±1–2%) require dramatically larger samples — halving the margin of error quadruples the sample size — so choose the largest margin that still meets your decision-making needs.