Is the coin fair?
Ask a precise question, compute an exact p-value, and interpret it correctly.
How surprising are these coin tosses?
Suppose the null hypothesis says a coin has a 50% chance of heads on each independent toss. Change the observed head count. The shaded bars show outcomes at least as far from the null mean as your observation: a two-sided exact binomial p-value.
Two-sided exact p-value—
Observed head proportion—
Null modelp = 0.50
Numerical probability table
| Heads | Probability if fair | Included in p-value? |
|---|
This assumes a pre-specified two-sided test and independent Bernoulli trials. The p-value is not the probability that the null hypothesis is true, nor the probability that the result occurred by chance.