Math & Education
P-Value Calculator (z, t, chi-square)
Get the p-value for a z-score, t-statistic or chi-square statistic — one- or two-tailed — and check it against your significance level.
How to use
- 1Choose the test statistic type and enter its value.
- 2Enter degrees of freedom for t and chi-square tests, and choose the tails.
How it's calculated
z: p = 1 − Φ(|z|) per tail. t: uses the Student's t distribution with df degrees of freedom. Chi-square: p = 1 − CDF(χ², df) (right tail).
Frequently asked questions
One-tailed or two-tailed?
Two-tailed tests any difference; one-tailed only a difference in the direction you predicted beforehand. Two-tailed is the safer default.
What does p < 0.05 mean?
If the null hypothesis were true, results at least this extreme would occur less than 5% of the time. It's not the probability the hypothesis is true.
Why is chi-square always right-tailed?
The chi-square statistic measures deviation, so only large values are evidence against the null hypothesis.
Three statistics, one underlying idea
A z, t or chi-square value all answer the same question — how far is this result from what you'd expect by chance? — but they come from different distributions depending on what you're testing and how much is known. Z assumes a known population standard deviation, t accounts for estimating it from a small sample (and needs degrees of freedom), and chi-square measures total squared deviation, which is why it's never negative and only ever tested in the right tail.
Doubling for two tails isn't just convention
A two-tailed test asks 'is this different in either direction?' while a one-tailed test commits beforehand to one direction only. Concretely, z = 1.96 gives a two-tailed p of 0.05 but a one-tailed p of about 0.025 — exactly half — because the one-tailed test only counts area in one side of the distribution. Choosing one-tailed after seeing your data (rather than before) inflates your apparent significance, which is why two-tailed is the more defensible default.
What a small p-value doesn't prove
p < 0.05 means: if the null hypothesis were actually true, a result this extreme would happen less than 5% of the time by chance. It is not the probability the null hypothesis is true, and it says nothing about the size or practical importance of the effect — a tiny, meaningless difference can still produce a small p-value with a large enough sample.
A negative z-score matches the positive one
For a z-score or a t-statistic, the sign is ignored. A result of −1.96 and a result of 1.96 are the same distance from zero, so they share one p-value. One-tailed uses the area in a single tail. Two-tailed doubles it. For 1.96 that two-tailed value is about 0.04999565. Chi-square hides the Tails menu and always uses the right-hand tail: the chance of a result at least this large. A negative chi-square, or fewer than 1 degree of freedom, is refused with the message that chi-square must be at least 0 and the degrees of freedom at least 1. A t-statistic needs at least 1 degree of freedom as well. The degrees-of-freedom box is hidden for a z-score, and the 10 that would otherwise sit there is not used.
z = 1.96 shows as 0.05 and is still called significant
Significant means the p-value is strictly smaller than the level you picked. Landing exactly on that level would read Not significant. The choices are 0.1, 0.05, 0.01, and 0.001, and the page starts at 0.05. The two-tailed p for z = 1.96 is about 0.04999565, which is just under 0.05, so the label is Statistically significant. The p-value itself is shown with at most five digits after the decimal, and 0.04999565 rounds to 0.05 on screen. You can see 0.05 and Significant together. z = 1.5, two-tailed, stays above 0.05 and reads Not significant. A chi-square of 3.841 with 1 degree of freedom is judged the same way: the label uses the full probability, not the five-digit figure in the box.
Related tools
- Grade Curve Calculator
Curve a set of test scores — raise the top score to 100, add a flat bonus, or scale to a target average — and see each student's new score.
- Chi-Square Test Calculator (Goodness of Fit & Contingency Table)
Run a chi-square goodness-of-fit test or a test of independence on a contingency table: get χ², degrees of freedom, the p-value and whether the result is significant.
- SAT to ACT Score Converter
Convert SAT scores to ACT composites and ACT to SAT using the official concordance tables — with approximate national percentiles to see how a score compares.
- Final Exam Grade Calculator
Find the score you need on the final exam to get the course grade you want, given your current grade and how much the final is worth.
- Test Score & Percentage Grade Calculator
Turn points earned into a percentage and letter grade — and see the grade for every number of wrong answers on a test.
- A/B Test Significance Calculator
Check whether an A/B test result is statistically significant — conversion rates, relative uplift, p-value and confidence using a two-proportion z-test.