MULTIPLE REGRESSION AS A FLEXIBLE ALTERNATIVE TO ANOVA IN L2 RESEARCH

Luke D Plonsky, Frederick L. Oswald

Research output: Contribution to journalArticle

22 Citations (Scopus)

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

Fingerprint

analysis of variance
regression
Analysis of Variance
Multiple Regression
language
Values

ASJC Scopus subject areas

  • Language and Linguistics
  • Education
  • Linguistics and Language

Cite this

MULTIPLE REGRESSION AS A FLEXIBLE ALTERNATIVE TO ANOVA IN L2 RESEARCH. / Plonsky, Luke D; Oswald, Frederick L.

In: Studies in Second Language Acquisition, 17.11.2016, p. 1-14.

Research output: Contribution to journalArticle

@article{9371c77cd2824b7dad03fbc076eb4dda,
title = "MULTIPLE REGRESSION AS A FLEXIBLE ALTERNATIVE TO ANOVA IN L2 RESEARCH",
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.",
author = "Plonsky, {Luke D} and Oswald, {Frederick L.}",
year = "2016",
month = "11",
day = "17",
doi = "10.1017/S0272263116000231",
language = "English (US)",
pages = "1--14",
journal = "Studies in Second Language Acquisition",
issn = "0272-2631",
publisher = "Cambridge University Press",

}

TY - JOUR

T1 - MULTIPLE REGRESSION AS A FLEXIBLE ALTERNATIVE TO ANOVA IN L2 RESEARCH

AU - Plonsky, Luke D

AU - Oswald, Frederick L.

PY - 2016/11/17

Y1 - 2016/11/17

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84995792499&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84995792499&partnerID=8YFLogxK

U2 - 10.1017/S0272263116000231

DO - 10.1017/S0272263116000231

M3 - Article

SP - 1

EP - 14

JO - Studies in Second Language Acquisition

JF - Studies in Second Language Acquisition

SN - 0272-2631

ER -