Statistical control in correlational studies: 10 essential recommendations for organizational researchers

• Published date: 01 February 2016
• Author: Guclu Atinc,Kevin D. Carlson,Paul E. Spector,Jeffrey R. Edwards,Thomas E. Becker,James A. Breaugh
• DOI: http://doi.org/10.1002/job.2053
• Date: 01 February 2016

Statistical control in correlational studies: 10

essential recommendations for organizational

researchers

THOMAS E. BECKER

1

*, GUCLU ATINC

2

, JAMES A. BREAUGH

3

,

KEVIN D. CARLSON

4

, JEFFREY R. EDWARDS

5

AND PAUL E. SPECTOR

6

1

College of Business, University of South Florida Sarasota–Manatee, Sarasota, Florida, U.S.A.

2

Department of Management, Texas A&M University–Commerce, Commerce, Texas, U.S.A.

3

College of Business Administration, University of Missouri–St. Louis, St. Louis, Missouri, U.S.A.

4

Pamplin College of Business, Virginia Tech, Blacksburg, Virginia, U.S.A.

5

Kenan-Flagler Business School, University of North Carolina, Chapel Hill, North Carolina, U.S.A.

6

Department of Psychology, University of South Florida, Tampa, Florida, U.S.A.

Summary Statistical control is widely used in correlational studies with the intent of providing more accurate estimates

of relationships among variables, more conservative tests of hypotheses, or ruling out alternative explanations

for empirical findings. However, the use of control variables can produce uninterpretable parameter estimates,

erroneous inferences, irreplicable results, and other barriers to scientific progress. As a result, methodologists

have provided a great deal of advice regarding the use of statistical control, to the point that researchers might

have difficulties sifting through and prioritizing the available suggestions. We integrate and condense this lit-

erature into a set of 10 essential recommendations that are generally applicable and which, if followed, would

substantially enhance the quality of published organizational research. We provide explanations, qualifica-

tions, and examples following each recommendation. Copyright © 2015 John Wiley & Sons, Ltd.

Keywords: statistical control; research methods; correlational studies

Organizational researchers often use statistical control in correlational studies, intending to provide more accurate

estimates of relationships among predictor and criterion variables, conduct more conservative tests of their hypoth-

eses, or rule out alternative explanations for empirical findings. However, including control variables (CVs) in anal-

yses raises a number of important conceptual and analytical issues. Methodologists have demonstrated that it is

important to address these issues because failing to do so can result in uninterpretable parameter estimates, cause

inferential errors, hinder replication of results, and in other ways hamper scientific progress (e.g., Burks, 1926;

Meehl, 1970; Spector, Zapf, Chen, & Frese, 2000).

Fortunately, recent authors have offered recommendations for properly using CVs in organizational research

(Atinc, Simmering, & Kroll, 2012; Becker, 2005; Breaugh, 2008; Carlson & Wu, 2012; Spector & Brannick,

2011). These articles have been cited more than 700 times, and the corresponding recommendations have been in-

corporated into the norms of the Academy of Management Journal and the Journal of Organizational Behavior

(Bono & McNamara, 2011; Edwards, 2008). Despite this attention, there appears to be little improvement in how

organizational researchers handle CVs. For example, Becker (2005) and Breaugh (2008) recommended that authors

provide clear justification for including CVs. Nonetheless, Bernerth and Aquinis (in press) reviewed 580 articles

containing CVs published in top management journals between 2003 and 2012 and found that in 2003, only 5%

of articles included a clear theoretical justification for including CVs. In 2012, the rate was 3%.

*Correspondence to: Thomas E. Becker, College of Business, University of South Florida Sarasota–Manatee, Sarasota, Florida, U.S.A. E-mail:

teb1@sar.usf.edu

Excepting the first author, the order of authorship is alphabetical.

Copyright © 2015 John Wiley & Sons, Ltd. Received 02 September2015, Accepted 05 September 2015

Journal of Organizational Behavior, J. Organiz. Behav. 37, 157–167 (2016)

Published online 25 September 2015 in Wiley Online Library (wileyonlinelibrary.com) DOI: 10.1002/job.2053

Researcher's Notebook