PaneliaTools

Sample size for a survey

You're preparing a survey — customer satisfaction, awareness, purchase intent — and the first budget question is always the same: how many respondents do you really need? The answer comes down to two parameters: the margin of error you accept and the confidence level you require. For a standard survey (±5%, 95%), plan on 385 respondents.

The calculator below is preset to those standard values. Adjust the margin to the stakes: a launch decision deserves ±3% (1,068 respondents), an exploratory signal can live with ±10% (97 respondents). If your target is limited — one retailer's customers, one city's residents — enter its size: the required sample drops noticeably.

Confidence level

95% is the market research standard. Z-scores: 1.645 · 1.96 · 2.576 (NIST statistical tables).

The acceptable gap between your sample and reality. ±5% is the most common choice.

If unsure, leave 50%: it's the worst case, requiring the largest sample.

The total number of people in your target. Above ~100,000 the impact is negligible: leave empty.

Respondents needed

385

You need 385 respondents for a 95% confidence level with a ±5% margin of error.

Export:

How many respondents per precision level?

Precision is expensive: going from ±5% to ±2% multiplies the sample by 6.

101001,00010,0001%3%5%8%10%Margin of error

Summary table

Sample size for the most common combinations.

Summary table
Confidence± 3%± 5%± 10%
90%75227168
95%1,06838597
99%1,844664166

Sample size: done. Now, the fieldwork…

Traditional fieldwork takes 6 weeks and $10,000. Panelia simulates 300+ calibrated respondents in 10 minutes.

Simulate my study

Frequently asked questions

How many respondents for a national survey?
Country size doesn't matter: 385 respondents give ±5% at 95% confidence, in France as in the US. Institutes often use 1,000 respondents to reach ~±3% and enable subgroup analysis.
Can I survey fewer people and stay credible?
Yes, by accepting a wider margin: 97 respondents give ±10%. That's honest as long as you display the margin next to your results — omitting it is what discredits a survey.
Should I account for non-responses?
Yes. The calculated size is the number of USABLE questionnaires. With an 80% completion rate, aim for 385/0.8 ≈ 482 invitations to end up with 385.
How do I analyze subgroups (age, region…)?
Each subgroup you want to read separately must reach its own sample size. To compare 4 age brackets at ±10% each, you need ~97 respondents PER bracket, not in total.