Analyzing Group Differences

Abstract

Many research questions in applied linguistics involve comparisons of group performance. Analysis of variance (ANOVA) is the procedure of choice in the majority of such analyses. This chapter identifies appropriate uses of ANOVA, explains how to conduct a statistically sound ANOVA, and also discusses null hypothesis testing and the importance of reporting and interpreting effect sizes in the context of means-based analyses. Use of some other statistical tools that are part of the general linear model (t-tests and multiple regression) for group mean comparisons are described with worked hypothetical examples. The chapter also describes the process of checking statistical assumptions, interpreting statistical output, and calculating effect sizes.