ERIC Number: EJ1152565
Record Type: Journal
Publication Date: 2017-Sep
Abstractor: As Provided
Multiple Regression as a Flexible Alternative to ANOVA in L2 Research
Plonsky, Luke; Oswald, Frederick L.
Studies in Second Language Acquisition, v39 n3 p579-592 Sep 2017
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.
Descriptors: Multiple Regression Analysis, Statistical Analysis, Comparative Analysis, Second Language Learning, Language Research, Educational Research, Theory Practice Relationship, Research Problems
Cambridge University Press. 100 Brook Hill Drive, West Nyack, NY 10994-2133. Tel: 800-872-7423; Tel: 845-353-7500; Fax: 845-353-4141; e-mail: firstname.lastname@example.org; Web site: http://journals.cambridge.org
Publication Type: Journal Articles; Reports - Evaluative
Education Level: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A