Overview

A p-value is the chance of seeing a result at least as extreme as yours if the null hypothesis were true. This converts a z, t or chi-square statistic into a p-value and a decision.

Enter the statistic, the degrees of freedom, a distribution code (1 z, 2 t, 3 chi-square), one or two tails, and alpha.

Worked examples

InputsResult
Test Statistic2.15Degrees of Freedom28DistributiontTailsTwo-tailedAlpha (%)5Distribution: tTest statistic: 2.15Degrees of freedom: 28p-value: 0.04Reject H0 at alpha=5%
Show 3 more examples
Test Statistic1.96Degrees of Freedom1Distributionz (normal)TailsTwo-tailedAlpha (%)5Distribution: zTest statistic: 1.96Degrees of freedom: 1p-value: 0.05Reject H0 at alpha=5%
Test Statistic3.84Degrees of Freedom1DistributionChi-squareTailsOne-tailedAlpha (%)5Distribution: chi-squareTest statistic: 3.84Degrees of freedom: 1p-value: 0.05Fail to reject H0 at alpha=5%
Test Statistic2.5Degrees of Freedom12DistributiontTailsTwo-tailedAlpha (%)5Distribution: tTest statistic: 2.5Degrees of freedom: 12p-value: 0.03Reject H0 at alpha=5%

How it works

For z, the p-value comes from the normal curve. For t and chi-square, it comes from those distributions with your degrees of freedom. If p is below alpha, the result is called significant.

Practical tips

  • z = 1.96, two-tailed, gives p ≈ 0.05.
  • You can check results in Excel with T.DIST.2T, NORM.S.DIST and CHISQ.DIST.RT.
  • Report the effect size alongside the p-value.

Frequently asked questions

What does p < 0.05 mean?

A result this extreme would happen less than 5% of the time if there were no real effect.

What does a p-value mean?

The chance of a result at least this extreme if the null hypothesis were true.

One or two tails?

Two, unless you decided before collecting data to test only one direction.