A Critical Review and Best‐Practice Recommendations for Control Variable Usage

By Jeremy B. Bernerth, Herman Aguinis. 2016

1,549 citations recorded by the source corpus.

Subfields: General Health Professions, Organizational Behavior and Human Resource Management

View Paper: https://www.semanticscholar.org/paper/ad4a58349208f6cdb4782d7231a249fd6cad6b42

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In General Health Professions

In Organizational Behavior and Human Resource Management

Citations in the corpus

Best-Practice Recommendations for Producers, Evaluators, and Users of Methodological Literature Reviews (2020, background): “…relevant given the rapid pace of methodological advancements (Cortina, Aguinis, & DeShon, 2017), which renders once commonly accepted practices, such as summarily excluding outliers or managing control variables (Aguinis, Hill, & Bailey, 2020; Bernerth & Aguinis, 2016), into potential QRPs.”
Psychological Capital: An Evidence-Based Positive Approach (2017, background): “Antecedents should not be relegated to a list of “usual suspects” that are often simply included as control variables in empirical studies with little justification (Bernerth & Aguinis 2016).”
MTurk Research: Review and Recommendations (2020, background): “Therefore, when Big Five traits are expected to influence substantive results, they can be used as statistical controls so that results and inferences are attributable to the hypothesized predictors and not to variability in personality traits between samples (Bernerth & Aguinis, 2016).”
Having a creative day: understanding entrepreneurs’ daily idea generation through a recovery lens (2018, result): “We also tested Models 3 and 4 without any controls to rule out the possibility that they are explaining or adjusting our results (Becker et al., 2016; Bernerth and Aguinis, 2016).”
When passion fades: disentangling the temporal dynamics of entrepreneurial passion for founding (2016, result): “As there was neither strong theory nor previous empirical research suggesting their inclusion, we excluded these controls from the main analyses reported in the paper – as is in line with recommendations from Bernerth and Aguinis (2016).”
HARKing: How Badly Can Cherry-Picking and Question Trolling Produce Bias in Published Results? (2019, background): “…results that do not reliably replicate (Derksen & Keselman, 1992; Harrell, 2011; Judd & McClelland, 1989).2 A prevalent yet not acknowledged instance of this mechanism is the choice of a particular set of control variables from several that are examined in a given study (Bernerth & Aguinis, 2016).”
Supervisor ostracism and defensive silence: a differential needs approach (2018, result): “Finally, we performed all the analysis both with and without control variables and found that our results were similar in both cases (Bernerth & Aguinis, 2016).”
Individual ambidexterity: the duality of exploration and exploitation and its relationship with innovative performance (2017, background): “Methodologists recommend that control variables should not be used uncritically (Becker et al., 2016; Bernerth & Aguinis, 2016).”