P-value calculator (z, t, chi-square, F)
Give your test statistic, its distribution and its degrees of freedom: the page computes the p-value.
Result
0.021234P-value
- If the null hypothesis were true, a result at least this extreme would happen about 2.1234% of the time.
- Left area P(X ≤ statistic)
- 0.989383
- Right area P(X ≥ statistic)
- 0.010617
- The p-value does not say whether the hypothesis is true or whether the effect matters. Pick the threshold (often 5%) before the test.
Inputs
- Distribution of the statistic
- Student t
- Value of the statistic
- 2.5
- Degrees of freedom
- 20
- Type of test
- Two-tailed
How it is calculated
Left = cumulative distribution F(x); right = 1 − F(x), each computed directly to stay accurate.
Result
P-value
- Left area P(X ≤ statistic)
- 0.989383
- Right area P(X ≥ statistic)
- 0.010617
How it is calculated
- Left = cumulative distribution F(x); right = 1 − F(x), each computed directly to stay accurate.
- Two-tailed = 2 × the smaller of the two areas (at most 1).
- t and F through the regularized incomplete beta function, z and chi-square through the regularized incomplete gamma function.
Example
t = 2.5 with 20 degrees of freedom, two-tailed: p ≈ 0.021234 (right area ≈ 0.010617).
Good to know
- No automatic decision: a p-value proves nothing on its own.
- Chi-square and F tests are almost always right-tailed; “two-tailed” simply doubles the smaller area.
- The result is only right if the statistic truly follows the chosen distribution (test conditions).
Frequently asked questions
What is this tool used for?
Give your test statistic, its distribution and its degrees of freedom: the page computes the p-value.
How is the result calculated?
Left = cumulative distribution F(x); right = 1 − F(x), each computed directly to stay accurate.
What should I check before using the result?
No automatic decision: a p-value proves nothing on its own.