A condition that holds true when both the variances across conditions are equal (this is the same as the homogeneity of variance assumption) and the covariances between pairs of conditions are also equal.

A condition that holds true when both the variances across conditions are equal (this is the same as the homogeneity of variance assumption) and the covariances between pairs of conditions are also equal.

• A. Compound symmetry
• B. Concurrent validity
• C. Confidence interval
• D. Complete separation

Answer: (A)

Compound symmetry is the idea that the same variance occurs at every condition and every pair of conditions has the same covariance. In a repeated-measures design, this means the covariance matrix has equal diagonal entries (variances) and equal off-diagonal entries (covariances), which also makes the correlations between any two conditions the same. This structure underpins the RM-ANOVA assumptions and helps ensure the standard tests behave as expected without extra corrections. The other terms don’t describe this covariance pattern—concurrent validity is about how a measure relates to a criterion measured now, a confidence interval is a range for a population parameter, and complete separation is a logistic-regression issue where a predictor perfectly predicts the outcome.

Compound symmetry is the idea that the same variance occurs at every condition and every pair of conditions has the same covariance. In a repeated-measures design, this means the covariance matrix has equal diagonal entries (variances) and equal off-diagonal entries (covariances), which also makes the correlations between any two conditions the same. This structure underpins the RM-ANOVA assumptions and helps ensure the standard tests behave as expected without extra corrections. The other terms don’t describe this covariance pattern—concurrent validity is about how a measure relates to a criterion measured now, a confidence interval is a range for a population parameter, and complete separation is a logistic-regression issue where a predictor perfectly predicts the outcome.