Repeated Measures ANOVA

Repeated measures ANOVA is a parametric test of whether the mean of a continuous outcome differs across three or more conditions or time points measured on the same subjects.

반복측정 분산분석은 같은 대상을 세 개 이상의 조건이나 시점에서 측정했을 때 연속형 결과변수의 평균이 다른지를 검정하는 모수 검정입니다.

How do I compare means across three or more time points measured on the same participants?

같은 참가자를 세 시점 이상 측정했을 때 평균을 어떻게 비교하나요?

Repeated measures ANOVA tests whether a continuous outcome's mean changes across three or more within-subject conditions or measurement occasions, removing stable individual differences from the error term. It fits balanced designs with complete data for every subject, and a Greenhouse-Geisser or Huynh-Feldt correction is applied when sphericity is violated.

When to use Repeated Measures ANOVA

• The same participants measured at three or more time points
• A within-subjects experiment with three or more conditions
• Several condition or occasion columns per subject on the same continuous scale

When to use something else

• Missing occasions or unequal measurement timing: use a linear mixed-effects model
• Ordinal or strongly non-normal outcomes: use the Friedman test

Assumptions and requirements

• Continuous outcome with complete data for each subject across conditions
• Sphericity, checked with Mauchly's test, or a corrected F test
• Approximately normal residuals with no extreme outliers
• Subjects independent of one another

What the analysis reports

• F statistic, degrees of freedom, and p-value
• Mauchly's test and Greenhouse-Geisser or Huynh-Feldt epsilon
• Partial or generalized eta squared
• Pairwise comparisons with Bonferroni adjustment
• Profile plot of condition means

How to report it

A repeated measures ANOVA with a Greenhouse-Geisser correction showed a significant effect of [factor] on [outcome], F([df1], [df2]) = [value], p = [value], ηp² = [value].

Related methods

• Friedman Test
• Linear Mixed-Effects Model
• Paired Samples t test

Run Repeated Measures ANOVA on Quorant