p-value Calculator
Turn a test statistic into a p-value. Choose the distribution, enter your statistic (and degrees of freedom where needed), and read off the p-value — computed with the same distribution functions as R’s pt(), pnorm() and pchisq().
How to use it
What the p-value means
The p-value is the probability of observing a test statistic at least as extreme as yours, if the null hypothesis were true. A small p-value means your data would be surprising under the null — evidence against it.
- Two-tailed tests look for a difference in either direction (the usual default).
- One-tailed tests look in a single, pre-specified direction — decide this before seeing the data, never after.
- Chi-square tests are upper-tailed by nature, so only that tail is offered.
A p-value is not the probability that the null is true, and it says nothing about effect size. Always report it alongside an effect size and a confidence interval.
Do it in R
2 * (1 - pt(2.1, df = 20)) # two-tailed t
1 - pchisq(6.0, df = 2) # chi-square (upper tail)FAQ
Frequently asked questions
One-tailed or two-tailed?
Use two-tailed unless you have a strong, pre-registered reason to test a single direction. Switching to one-tailed after seeing the data inflates your false-positive rate.
What does p < 0.05 actually tell me?
That an effect this large is unlikely under the null hypothesis — not that the effect is large or important. Interpret it together with the effect size and confidence interval.
A p-value is one number in a larger story. Need the whole analysis done properly? We can help.