NotesFAQContact Us
Search Tips
ERIC Number: ED447214
Record Type: Non-Journal
Publication Date: 2000
Pages: 27
Abstractor: N/A
Reference Count: N/A
An Empirical Investigation of Four Tests for Interaction in the Context of Factorial Analysis of Covariance.
Headrick, Todd C.; Vineyard, George
The Type I error and power properties of the parametric F test and three nonparametric competitors were compared in terms of 3 x 4 factorial analysis of covariance layout. The focus of the study was on the test for interaction either in the presence or absence of main effects. A variety of conditional distributions, sample sizes, levels of variate and covariate correlation, and treatment effect sizes were investigated. The Puri and Sen (M. Puri and P. Sen, 1969) test had ultra-conservative Type I error rates and power losses when main effects were present. The adjusted rank transform (R. Blair and H. Sawilowsky, 1990; K. Salter and R. Fawcett, 1993) had liberal Type I error rates when sampling was from moderate to extremely skewed distributions. The Hettmansperger (T. Hettmansperger, 1984) chi-square test displayed acceptable Type I error rates for all distributions considered when sample sizes were 10 or 20. It is suggested that the Hettmansperger test be considered as an alternative to the parametric "F" test provided sample seizes are relatively equal and at least as large as 10. (Contains 13 tables and 23 references.) (Author/SLD)
Publication Type: Reports - Evaluative
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A