Linked from

The 29 pages that link to Statistical power, each with the reason it gives.

• Randomized controlled trialRelated: Power calculations guide how many participants a trial needs.

• Replication crisisRelated: Low power makes estimated effects unstable and genuine findings harder to reproduce.

• Gene–environment interactionRelated: Interaction effects are often small and require larger samples than main effects.

• Statistical inferenceRelated: Power shows why a non-significant result does not establish absence of an effect.

• P-valueRelated: Power helps explain why a large p-value does not establish that an effect is absent.

• Experimental designRelated: Sample size and variability determine whether a planned study can detect its target effect.

• Statistical significanceRelated: Power affects how readily a study detects effects at its chosen significance level.

• Multiple comparisons problemRelated: Corrections that reduce false positives can also reduce power to detect real effects.

• Field experimentRelated: Field experiments need enough independently assigned units to detect plausible effects.

• A/B testingRelated: Power planning helps avoid interpreting an inconclusive small experiment as proof of no effect.

• Null hypothesisRelated: Power describes how often a test detects a departure from the reference condition.

• Effect sizeRelated: Power depends partly on the effect size a study is designed to detect.

• ReplicationRelated: Low power makes genuine effects harder to detect in both original and repeated studies.

• Placebo-controlled trialRelated: A weak placebo contrast can leave a trial unable to detect meaningful differences.

• Scientific reproducibilityRelated: Underpowered studies can produce unstable estimates that fail to recur.

• Statistical hypothesis testingRelated: Power describes detection probability alongside the risk of a false rejection.

• Frequentist statisticsRelated: Power quantifies a test’s ability to detect effects under repeated sampling.

• Quantitative researchRelated: Low power can leave real relationships undetected in quantitative studies.

• Type I and type II errorsRelated: Power equals one minus the type II error probability for that alternative.

• Control groupRelated: Too few control participants can leave meaningful intervention effects undetected.

• Egon PearsonRelated: Power measures a test's ability to detect the alternatives Pearson and Neyman considered.

• Sample sizeRelated: Increasing sample size often raises the chance of detecting a real effect.

• BiostatisticsRelated: Power calculations help determine whether a study can detect effects of practical importance.

• Jerzy NeymanRelated: Power expresses a test’s ability to detect departures from its null hypothesis.

• Neyman–Pearson lemmaRelated: The lemma maximizes this probability among tests of equal size.

• Frequentist inferenceRelated: Power is the repeated-sample chance of detecting an effect under an alternative.

• Sample size determinationRelated: Power-based calculations set sample size to make detecting a target effect sufficiently likely.

• Statistical hypothesis testRelated: It describes the test's chance of detecting a departure of a given size.

• Michael KremerRelated: Adequate sample sizes matter when evaluating programs whose effects may be modest.