P-Value Calculator - Z, T, F & Chi-Square Tests

The p-value is the probability of obtaining a test statistic at least as extreme as the one actually observed, assuming the null hypothesis is true. It is the core output of almost every classical statistical test and serves as the primary criterion for deciding whether to reject the null hypothesis. A small p-value means the observed data are unlikely under the null hypothesis, which is evidence in favour of the alternative hypothesis. The procedure begins with a null hypothesis H₀ (typically a statement of no effect, no difference, or no association) and an alternative hypothesis H₁. You collect data, compute a test statistic (Z, t, F, or χ²), and then use the probability distribution of that statistic under H₀ to find the p-value. If the p-value is less than or equal to your pre-specified significance level α (most commonly 0.05), you reject H₀ and declare the result statistically significant. Different test statistics follow different probability distributions. The Z-statistic follows a standard normal distribution and is used when the population standard deviation is known or the sample is very large. The t-statistic follows a Student's t-distribution with a specific number of degrees of freedom (df = n − 1 for a one-sample test) and is used for small-to-moderate samples when the population standard deviation is unknown. The F-statistic follows an F-distribution with numerator and denominator degrees of freedom and is the basis for ANOVA and the F-test for equality of variances. The Chi-square statistic follows a Chi-square distribution with df degrees of freedom and is used for tests of independence in contingency tables and goodness-of-fit tests. The tail type determines which region of the distribution is used to compute the p-value. A two-tailed test is appropriate when the alternative hypothesis is non-directional (H₁: μ ≠ μ₀) and the p-value sums the probability in both extremes. A right-tailed test applies when H₁ specifies a positive direction (H₁: μ > μ₀), and a left-tailed test when H₁ specifies a negative direction (H₁: μ < μ₀). For the F-test and Chi-square test, which are inherently one-sided in practice (the test statistic cannot be negative), the right-tailed p-value is the standard reported value. A critical and common misconception is that the p-value is the probability that H₀ is true. It is not. The p-value is a conditional probability: P(data this extreme | H₀ is true). It says nothing about the probability that H₀ or H₁ is true; for that you need Bayesian inference with prior probabilities. Another misconception is that p < 0.05 means the effect is large or practically important. Statistical significance depends on sample size — with a large enough sample, even a trivially small and meaningless effect will yield p < 0.05. Always report effect sizes alongside p-values. The significance level α should be decided before looking at the data and should reflect the tolerable risk of a false positive (Type I error). Different fields use different conventions: α = 0.05 is standard in most biomedical and social science research, α = 0.01 is common when false positives are costly, and α = 5 × 10⁻⁸ is used in genome-wide association studies to account for the large number of tests performed simultaneously. This calculator supports α values of 0.01, 0.05, and 0.10.