Second language (L2) research relies heavily and increasingly on ANOVA (analysis of variance)-based results as a means to advance theory and practice. This fact alone should merit some reflection on the utility and value of ANOVA. It is possible that we could use this procedure more appropriately and, as argued here, other analyses such as multiple regression may prove to be more illuminating in certain research contexts. We begin this article with an overview of problems associated with ANOVA; some of them are inherent to the procedure, and others are tied to the way it is applied in L2 research. We then present three rationales for when researchers might turn to multiple regression in place of ANOVA. Output from ANOVA and multiple regression analyses based on published and mock-up studies are used to illustrate major points.