Linked from

The 28 pages that link to Statistical significance, each with the reason it gives.

• Confidence intervalCompared with: Interval exclusion of a null value can correspond to a significance decision, but the concepts are not interchangeable.

• Scientific skepticismRelated: It is often mistaken for proof, though it answers a narrower question.

• Statistical inferenceRelated: It is a common but limited way to summarize evidence from a test.

• P-valueRelated: The threshold turns a continuous p-value into a conventional decision label.

• Corpus linguisticsRelated: It helps assess whether corpus frequency differences exceed random variation.

• Multiple comparisons problemRelated: An unadjusted significance threshold is commonly applied to each comparison.

• A/B testingRelated: It helps assess whether an observed difference exceeds what random variation might explain.

• Effect sizeCompared with: A small effect can be statistically significant with enough data, while a large estimate can remain uncertain.

• Statistical hypothesis testingRelated: Its conventional threshold is often mistaken for evidence of practical importance or truth.

• ATLAS experimentRelated: ATLAS uses significance to assess whether an excess over background supports a discovery claim.

• Karl PearsonRelated: Pearson’s testing framework helped shape significance testing, whose interpretation remains disputed.

• Type I and type II errorsRelated: Significance is a decision threshold, not proof that a finding is true or important.

• Egon PearsonRelated: Pearson's framework formalizes thresholds, but significance alone does not establish practical importance.

• Margin of errorRelated: A margin can show whether a confidence interval includes a null value, but significance is not the same as practical importance.

• Precision measurementCompared with: A precise measurement is not automatically evidence that an effect matters scientifically.

• ArchaeoastronomyRelated: Statistical tests help distinguish intentional patterns from alignments that occur by chance.

• Ganzfeld experimentRelated: Above-chance matching is assessed statistically rather than by impression alone.

• Quantitative dataRelated: Numerical evidence can cross a significance threshold without implying a large or useful effect.

• Null hypothesis significance testingRelated: The test's decision is conventionally reported using this term.

• ApopheniaCompared with: Formal tests can assess whether an apparent pattern exceeds what chance predicts.

• Statistical hypothesis testRelated: The label records a threshold crossing, not the importance or truth of a finding.

• The New England Journal of MedicineRelated: Interpreting reported findings requires distinguishing statistical evidence from clinical importance.

• Huge-LQGRelated: A structure's apparent size alone does not establish that it is cosmologically anomalous.

• John ArbuthnotRelated: His argument from a long run of male-biased births anticipated reasoning about unlikely patterns.

• Large quasar groupRelated: The claimed unusualness of a group depends on its significance under an explicit clustering model.

• Birthday-number effectRelated: A statistically detectable preference does not by itself show a large or consequential real-world effect.

• Dark flowRelated: The claim depends on whether its reported signal survives robust significance tests.

• Eyeball theoremRelated: A graph's apparent difference does not determine whether a result crosses a significance threshold.