Linked from

The 32 pages that link to P-value, each with the reason it gives.

• Confidence intervalCompared with: A p-value tests a hypothesis; it is not the probability that a parameter lies within an interval.

• Sampling distributionRelated: Its calculation depends on the statistic's null sampling distribution.

• Statistical inferenceRelated: Misreading p-values can turn a calibrated test result into an unsupported claim.

• Statistical powerCompared with: A p-value summarizes observed data under the null; power is a prospective rejection probability under alternatives.

• Analysis of varianceRelated: ANOVA reports a p-value for evidence against its null, not the probability that the null is true.

• Statistical significanceRelated: It quantifies the data’s extremeness under the null, not the probability the null is true.

• Multiple comparisons problemRelated: Repeatedly screening p-values creates more chances for a seemingly small value.

• Null hypothesisRelated: It quantifies tail-area evidence against the null, without giving the probability that the null is true.

• Ronald FisherCompared with: Fisher treated the p value as a graded measure of evidence, unlike fixed-threshold testing.

• Effect sizeCompared with: Unlike an effect size, it does not directly quantify magnitude.

• Bayesian statisticsCompared with: Its frequentist interpretation differs from the posterior probability statements Bayesian analyses permit.

• StatisticsBroader topic: Misreading it as the probability that a hypothesis is true has distorted scientific claims.

• Likelihood ratioCompared with: A p-value measures tail-area extremity, not the relative probability of evidence under two hypotheses.

• Statistical hypothesis testingRelated: It quantifies tail-area compatibility under the null, not the probability that the null is true.

• Frequentist statisticsBroader topic: It quantifies extremeness under the null, not the probability that the null hypothesis is true.

• Quantitative researchRelated: Misinterpretation of p-values can turn statistical evidence into overstated claims.

• Bayes factorCompared with: A p-value is not the probability of a model or the ratio of two models’ evidence.

• Posterior probabilityCompared with: A p-value is not the probability that a hypothesis is true after seeing data.

• Type I and type II errorsRelated: Comparing it with the significance level determines whether the test rejects the null.

• Egon PearsonCompared with: Fisher treated the p-value as a measure of evidence, unlike a fixed decision rule.

• Sample sizeRelated: With sufficiently large samples, even small effects can produce small p-values.

• BiostatisticsRelated: Its interpretation is central to reported evidence and frequently misunderstood in medical studies.

• Frequentist probabilityBroader topic: Its frequentist meaning depends on hypothetical repetitions under the null model.

• Jerzy NeymanCompared with: A p-value is not the same as Neyman’s prechosen long-run decision rule.

• Student's t-testRelated: The t-distribution converts the test statistic into evidence against the null hypothesis.

• Null hypothesis significance testingRelated: The test compares this tail probability with its preset significance level.

• Frequentist inferenceBroader topic: It measures how surprising the observation is under the tested null, not the probability that the null is true.

• Chi-squared testRelated: It expresses how unusual the computed statistic is under the null model.

• Credible intervalCompared with: It is a tail probability under a null model, not posterior probability assigned to parameter values.

• Statistical hypothesis testBroader topic: It measures how unusual the observed statistic would be if the null model held.

• Statistical analysisBroader topic: Its interpretation is central to many statistical tests and often misunderstood.

• Eyeball theoremCompared with: It quantifies evidence against a null model rather than relying on apparent separation.