NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED457192
Record Type: Non-Journal
Publication Date: 1998-Apr
Pages: 31
Abstractor: N/A
Reference Count: N/A
ISBN: N/A
ISSN: N/A
A Procedure for Testing the Difference between Effect Sizes.
Lambert, Richard G.; Flowers, Claudia
A special case of the homogeneity of effect size test, as applied to pairwise comparisons of standardized mean differences, was evaluated. Procedures for comparing pairs of pretest to posttest effect sizes, as well as pairs of treatment versus control group effect sizes, were examined. Monte Carlo simulation was used to generate Type I error rates and power values for tests of the differences in independent effect sizes based on both the "g" and "d" methods. Type I error rate was evaluated by crossing 6 sample size conditions (5, 10, 20, 30, 50, and 100) by 5 population effect size conditions (0.00, 0.25, 0.50, 0.75, and 1.00). Power was evaluated by crossing the 6 sample size conditions by 4 conditions representing the magnitude of the difference between treatment and control conditions (0.25, 0.50, 0.75, and 1.00). The "d" based statistic yielded Type I error rates closer to the nominal level than did the "g" based statistic while yielding a slightly more conservative method for testing the difference between two effect size measures. Examples are provided that illustrate the use of these procedures as post hoc comparison techniques following factorial analysis of variance designs. (Contains 6 tables and 30 references.) (Author/SLD)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A