Search the complete library

What do you want to learn or calculate?

Quick linksAll calculatorsMath subjectsPractice questionsFormula library
← Statistics formulas

Margin of error

Express the half-width of a confidence interval.

Statistics · Estimation
$$ME=(\text{critical value})(\text{standard error})$$

Margin of error is one of 1 estimation formula in the statistics section of this library, and it is used at ap · university level.

Why margin of error works

It is half the width of a confidence interval, expressing how far the estimate could plausibly sit from the truth. Two ingredients decide it: how noisy the estimate is, captured by the standard error, and how sure you insist on being, captured by the critical value.

What each symbol means

The critical value comes from a confidence level and reference distribution.

Margin of error: when it holds

Use a standard-error formula and critical distribution appropriate to the parameter and assumptions.

When it stops applying

It assumes the sample was drawn at random from the population you want to describe. If it was not, the interval is centred on the wrong number, and quoting plus or minus 3 percent around a biased estimate simply attaches false precision to a wrong answer.

Margin of error: a worked example

If $z^*=1.96$ and $SE=0.03$, then $ME=0.0588$.

The mistake to avoid

What people do: Treating it as a bound on every kind of error in the study.

Why it goes wrong: It only covers the luck of which cases were drawn. Nonresponse, a leading question, an out-of-date list of who to contact, and people who answer untruthfully are all outside it entirely.

Do this instead: Report the margin alongside a note on how the sample was collected, and treat design problems as separate issues that no arithmetic can measure.

Margin of error: step by step

  1. Name the unknown, and the unit the answer has to come out in.
  2. Match the symbols to your values. The critical value comes from a confidence level and reference distribution.
  3. Check the conditions before substituting. Use a standard-error formula and critical distribution appropriate to the parameter and assumptions.
  4. Substitute, keep exact values to the last line, then test the sign, size, and unit against a rough estimate — the check that catches most statistics slips.

Where this formula fits

Subject
Statistics formulas — 21 entries in this library
Topic
Estimation
Level
AP · University

Formulas are easiest to keep when they sit inside a method rather than on a list. Use the links below to see where margin of error comes from, to check a calculation against a tool, and to practise it until you can recall it without looking.

Questions about margin of error

Why do national polls so often quote plus or minus 3 percent?

Because roughly a thousand respondents produce it. With about 1067 people at 95 percent confidence and the worst-case proportion of 0.5, the margin works out to almost exactly 0.030.

Does a bigger population require a bigger sample?

No, and this surprises most people. The sample size appears in the formula but the population size does not, so a country of 300 million needs no larger a sample than a city of 300 thousand.

How much does moving from 95 to 99 percent confidence widen it?

By a factor of 2.576 over 1.960, which is about 1.31. Demanding that extra certainty makes your reported range roughly 31 percent wider on the same data.

Can I shrink the margin by lowering my confidence level?

Yes, arithmetically, but you are not learning anything more. A narrow interval at 80 percent confidence is a weaker claim, not a more precise measurement.

Stuck on a problem?

Work a margin of error problem step by step

Type your own problem, or upload a photo of it. You get the method, the answer, and a check you can repeat yourself.