|Saturday, February 22|
|PS3 Poster Session III & Continental Breakfast||
Sat, Feb 22, 7:30 AM - 9:00 AM
An Introduction to the Generalized Eta-Squared Effect Size Associated with Analysis of Variance Models (302837)*Anh P. Kellermann, University of South Florida
Keywords: generalized eta-squared, effect sizes, ANOVA, SAS/STAT
Commonly reported effect sizes for ANOVA models include eta-squared, partial eta-squared, omega-squared, and partial omega-squared. Although there are important differences among these indices, the choice of an effect size for ANOVA models can be confusing because these indices might differ depending on the research design and magnitude of the effect. In addition, they can be misinterpreted. Olejnik and Algina (2003) proposed the generalized eta-squared effect size whose value is not influenced by the study research design and consequently is comparable across a wide variety of ANOVA designs. However, the generalized eta-squared effect size is not readily available in packaged computer programs and not commonly used. This presentation provides an overview of the generalized eta-squared statistic and presents a SAS macro to facilitate its computation in a variety of ANOVA designs.