The regression discontinuity design has been used in several studies in management research. Below, you will find a brief summary of the studies.
Arvate, Galilea and Todescat (2018)
The authors apply the regression discontinuity design to answer the question whether female top-managers disadvantage women in the organization, e.g., by reducing their chances to get promoted to management positions (the so-called “queen bee theory”). The study uses mayoral elections in Brazilian municipalities to answer the question. The idea is that in close elections (i.e., elections in which the difference between the male candidate and the female candidate is <5 percent), the assignment of a male/female leader is almost random. The most important finding of the study is that the number of female top and middle managers in public organizations increases in municipalities in which a woman was elected mayor (treatment group) compared with municipalities in which a male was elected (control group). Thus, the study provides no evidence for a “queen bee effect”, but rather suggests a “regal leader effect” of women in top-management positions.
Flammer uses the regression discontinuity design to analyze the (causal) relationship between CSR implementation and firm performance. Her study focuses on CSR proposals that pass or fail by a small margin of shareholder votes (so-called “close call CSR proposals”). Her argument is that near the pass/fail threshold (i.e., 50.1 percent of the votes), the assignment of CSR to companies is almost random (i.e., there is no real difference between companies that are close to the threshold except for the fact that some of these companies have implemented CSR whereas others have not). Her study found a positive relationship between the implementation of CSR and both announcement returns and firms’ accounting performance. However, she also showed that close call CSR proposals differ from non-close proposals along several dimensions, which suggests that although adopting close call CSR proposals is beneficial to some companies, it is not necessarily beneficial to all companies.