MULTIPLE REGRESSION AS A FLEXIBLE ALTERNATIVE TO ANOVA IN L2 RESEARCH

Luke D Plonsky, Frederick L. Oswald

Research output: Contribution to journalArticle

34 Scopus citations

Abstract

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.

Original languageEnglish (US)
Pages (from-to)1-14
Number of pages14
JournalStudies in Second Language Acquisition
DOIs
StateAccepted/In press - Nov 17 2016
Externally publishedYes

ASJC Scopus subject areas

  • Language and Linguistics
  • Education
  • Linguistics and Language

Fingerprint Dive into the research topics of 'MULTIPLE REGRESSION AS A FLEXIBLE ALTERNATIVE TO ANOVA IN L2 RESEARCH'. Together they form a unique fingerprint.

  • Cite this