| Title |
The choice of control variables in empirical management research: How causal diagrams can inform the decision / |
| Authors |
Huenermund, Paul ; Louw, Beyers ; Rönkkö, Mikko |
| DOI |
10.1016/j.leaqua.2024.101845 |
| Full Text |
|
| Is Part of |
Leadership quarterly.. New York : Elsevier Inc.. 2024, In Press, Corrected proof, p. [1-15].. ISSN 1048-9843 |
| Keywords [eng] |
causal inference ; control variables ; directed acyclic graphs ; regression analysis ; structural causal models |
| Abstract [eng] |
The Leadership Quarterly and the management community more broadly prioritize identifying causal relationships to inform effective leadership practices. Despite the availability of more refined causal identification strategies, such as instrumental variables or natural experiments, control variables remain a common strategy in leadership research. The current literature generally agrees that control variables should be chosen based on theory and that these choices should be reported transparently. However, the literature provides little guidance on how specifically potential controls can be identified, how many control variables should be used, and whether a potential control variable should be included. Consequently, the current empirical literature is not fully transparent on how controls are selected and may be contaminated with bad controls that compromise causal inference. Causal diagrams provide a transparent framework to address these issues. This article introduces causal diagrams for leadership and management researchers and presents a workflow for finding an appropriate set of control variables. |
| Published |
New York : Elsevier Inc |
| Type |
Journal article |
| Language |
English |
| Publication date |
2024 |
| CC license |
|
