Free online formula calculators

Margin of Error Calculator

Find the plus-or-minus margin of error for a proportion measured in a survey, given the sample size and confidence level.

Margin of Error Calculator
%
%
Result
Margin of error3.10%
Lower bound48.90%
Upper bound55.10%
Standard error1.580%

Link to this calculation

Formula

E = z × √( p(1 − p) ÷ n ) × √( (N − n) ÷ (N − 1) )
SymbolMeaning
EMargin of error
zCritical value for the confidence level
pSample proportion
nSample size
NPopulation size (the last factor is dropped when N is blank)

How to Use This Calculator

  1. Enter the Sample size.
  2. Enter the Sample proportion (%). The percentage who gave a particular answer.
  3. Enter the Confidence level (%).
  4. Enter the Population size. Optional; leave blank for a large population.
  5. Press Calculate. Results also update automatically as you type.

Worked Example

Using the values pre-filled in the calculator above:

Inputs
Sample size1,000
Sample proportion52 %
Confidence level95 %
Population size0
Results
Margin of error3.10%
Lower bound48.90%
Upper bound55.10%
Standard error1.580%

About This Calculation

The margin of error is the "plus or minus" figure attached to poll results. If a poll of 1,000 voters finds 52% support with a ±3.1% margin at 95% confidence, the method used would capture the true level of support within that band in 95 out of 100 repeated samples. In other words, real support is plausibly anywhere from about 48.9% to 55.1%.

The margin shrinks with the square root of the sample size, so quadrupling the number of respondents only halves the margin. It is largest when the proportion is near 50% and smaller near 0% or 100%. Raising the confidence level from 95% to 99% widens the margin because you are asking for more certainty.

Be careful when comparing two candidates in the same poll: the margin on the gap between them is roughly double the stated margin. Subgroups, such as voters under 30, have much smaller samples and therefore much larger margins. Most importantly, the margin of error only covers random sampling error. It says nothing about biased question wording, people who refuse to answer, or samples that do not represent the population, which are often bigger sources of error in practice.

Frequently Asked Questions

What is a good margin of error?
Most opinion polls aim for about ±3% to ±5% at 95% confidence. Anything above ±10% is usually too imprecise for decisions.
Does population size affect the margin of error?
Only when the sample is a sizeable fraction of the population, roughly 5% or more. Enter the population size to apply the finite population correction in that case.
How many people do I need for a ±3% margin?
About 1,068 at 95% confidence for a large population. Use the sample size calculator for other targets.

Category: Statistics & Probability. Found a problem with this calculator? Let us know.