On Testing the Trial-by-Subject Interaction for the Shine Combined Analysis of Variance

Abstract

An alternate procedure is presented for testing the trial-by-subject interaction in the Shine Combined ANOVA. This new procedure is designed to get around the independence and distributional problems of the original F test.

Get full access to this article

View all access options for this article.

References

Shine, L. C. Independence problems for certain tests based on the Shine-Bower error term. EDUCATIONAL AND PSYCHOLOGICAL MEASURMENT, 1975, 35, 535-537.

Shine, L. C. An alternate statistic for testing the slow change assumption of the Shine-Bower error term. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1976, 36, 611-614.