A heteroscedastic, rank-based approach for analyzing 2 x 2 independent groups designs

Mills, L.Cribbie, RobertLuh, Wei-ming2018-06-032018-06-032009Mills, Laura; Cribbie, Robert A.; and Luh, Wei-Ming (2009) "A Heteroscedastic, Rank-Based Approach for Analyzing 2 x 2 Independent Groups Designs," Journal of Modern Applied Statistical Methods, 8(1), 322-336. doi: 10.22237/jmasm/12411378001538 – 9472DOI: 10.22237/jmasm/1241137800http://hdl.handle.net/10315/34601The ANOVA F is a widely used statistic in psychological research despite its shortcomings when the assumptions of normality and variance heterogeneity are violated. A Monte Carlo investigation compared Type I error and power rates of the ANOVA F, Alexander-Govern with trimmed means and Johnson transformation, Welch-James with trimmed means and Johnson Transformation, Welch with trimmed means, and Welch on ranked data using Johansen’s interaction procedure. Results suggest that the ANOVA F is not appropriate when assumptions of normality and variance homogeneity are violated, and that the Welch/Johansen on ranks offers the best balance of empirical Type I error control and statistical power under these conditions.enFactorial ANOVAWelch factorial testnon-normalityvariance heterogeneityA heteroscedastic, rank-based approach for analyzing 2 x 2 independent groups designsArticlehttps://digitalcommons.wayne.edu/jmasm/https://digitalcommons.wayne.edu/https://digitalcommons.wayne.edu/jmasm/vol8/iss1/31/?utm_source=digitalcommons.wayne.edu%2Fjmasm%2Fvol8%2Fiss1%2F31&utm_medium=PDF&utm_campaign=PDFCoverPages