Confidence Interval Calculator

  • Tested against OpenStax examples and 80 cases worked to 60 digits by an independent program
  • Checked by Wayne Bickerton
  • Sources: OpenStax
  • Updated November 11, 2026

A sample’s average is only an estimate of the true average. A confidence interval gives the range the true mean is likely to be in. Type your sample mean, standard deviation, sample size and confidence level to get the interval, the margin of error and the steps.

%
Confidence interval
67.1776 – 68.8224 90% confidence

We estimate with 90% confidence that the true mean is between 67.1776 and 68.8224.

Margin of error ± 0.8224
z-score 1.6449
Standard error 0.5

What is a confidence interval?

A confidence interval is a range, worked out from a sample, that is likely to contain the true mean. A 90% confidence level means that if you took many samples and built an interval from each one in the same way, about 90% of those intervals would contain the true mean. A higher level gives a wider interval; a bigger sample gives a narrower one.

Source OpenStax · Introductory Statistics 2e, 8.1 A Single Population Mean using the Normal Distribution ↗

How to calculate a confidence interval

Interval = x̄ ± z × σ ÷ √n

Here it is with your numbers:

  1. For 90% confidence, z = 1.6449
  2. Standard error: 3 ÷ √36 = 0.5
  3. Margin of error: 1.6449 × 0.5 = 0.8224
  4. Interval: 68 ± 0.8224, from 67.1776 to 68.8224.

It means that if you took many samples of 36 and worked out an interval this way each time, about 90% of the intervals would contain the true mean.

Confidence interval at 80%, 90%, 95%, 98% and 99%

For the numbers above:

LevelMargin of errorInterval
80%± 0.640867.3592 – 68.6408
90%± 0.822467.1776 – 68.8224
95%± 0.9867.02 – 68.98
98%± 1.163266.8368 – 69.1632
99%± 1.287966.7121 – 69.2879

Known standard deviation, or from your sample?

This calculator uses the normal curve (z-scores), which is right when you know the standard deviation of the whole population. In practice it usually comes from the sample itself. Then the Student’s t-distribution is the standard choice, and it gives a slightly wider interval, most of all for small samples.

Source OpenStax · Introductory Statistics 2e, 8.2 A Single Population Mean using the Student t Distribution ↗

Confidence interval examples

ExampleInterval
Exam scores (OpenStax 8.2)67.1776 – 68.8224
The same, at 95% (OpenStax 8.4)67.02 – 68.98
Phone radiation, SAR (OpenStax 8.3)0.8809 – 1.1671

FAQs

How do I calculate a 95% confidence interval?

Work out 1.96 × standard deviation ÷ √(sample size), then subtract it from and add it to the mean. For a mean of 68, a standard deviation of 3 and 36 people, 1.96 × 3 ÷ 6 is 0.98, so the 95% interval is 67.02 to 68.98.

Source OpenStax · Introductory Statistics 2e, 8.1 A Single Population Mean using the Normal Distribution ↗

How do you calculate a confidence interval?

Mean ± z × standard deviation ÷ √n. The z-score depends on the confidence level: 1.6449 for 90%, 1.96 for 95% and 2.5758 for 99%. The part after ± is the margin of error (error bound).

Sources

Related calculators