Free Sample Size Calculator for Surveys

Work out how many respondents you need for a survey. Enter your population, confidence level and margin of error. This is the same standard formula used in market research and in PhD and MBA projects.

Population size (leave blank if very large or unknown)

Confidence level

Margin of error (%)

Expected proportion (%) (use 50 if unsure: it gives the safest, largest sample)

The formula

For a large population: n = Z² × p(1 − p) / e². For a known population N, the sample is adjusted: n / (1 + (n − 1) / N). Z is 1.645, 1.96 or 2.576 for 90%, 95% and 99% confidence.

Quick reference (95% confidence, p = 50%)

Margin of error	Sample (large population)
±10%	97
±7%	197
±5%	385
±3%	1,068

Tips for students and researchers

If you analyse sub-groups (for example by gender or city), each sub-group needs enough respondents too.
For qualitative studies (interviews, focus groups) sample size works differently: usually 8 to 30 interviews until themes repeat.
Random sampling matters as much as sample size. A large biased sample is still biased.

Need the fieldwork done?

ARS Market Research Services, Chennai, collects survey data across India for companies, students and PhD scholars. See PhD field data collection, consumer research and free survey questionnaire templates, or write to admin@arsmrs.in or WhatsApp +91 97899 76662.