PaneliaTools

5% margin of error: the sample size

±5% is the most used margin of error in quantitative research: fine enough to settle most marketing decisions, wide enough to stay affordable. The number to remember: 385 respondents at 95% confidence (large population, cautious 50% proportion). That's exactly this calculator's preset.

Concretely, ±5% means a score measured at 60% reflects a reality between 55% and 65%. Enough to separate 60% from 40%; not enough to separate 52% from 48% — in that case, tighten the margin to ±3% (1,068 respondents) or ±2% (2,401). The chart under the result shows this precision/cost trade-off at a glance.

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

Why exactly 385 respondents?
n = 1.96² × 0.5 × 0.5 / 0.05² = 384.16, rounded up: 385. With a finite population entered, the FPC lowers that figure (278 for 1,000 people).
±5% on what kind of result?
On proportions (percentages of answers). For means (an average price, a 0–10 score), the formula differs: it depends on the observed standard deviation, not on p·(1−p).
Does my margin apply to every result in the survey?
It's maximal for scores near 50% and tightens at the extremes: a 90% score measured with n = 385 has an actual margin of about ±3%. ±5% is therefore a cautious guarantee.
What if I slice by subgroups?
The ±5% margin applies to the TOTAL sample. A 100-respondent subgroup has its own margin (±9.8%). Size every segment you want to analyze separately.