On the causality and plausibility of treatment effects in operations management research

Abstract

Empirical research in operations management (OM) has made rapid strides in the last 30 years, and increasingly, OM researchers are leveraging methods used in the econometrics and statistics literature to assess the causal effects of interventions. We discuss the two key challenges in assessing causality with observational data (i.e., baseline bias, differential treatment effect bias) and how dominant identification approaches such as matching, instrumental variables, regression discontinuity, difference‐in‐differences, and fixed effects deal with such challenges. We surface the key underlying assumptions of different causal estimation methods and discuss how OM scholars have used these methods in the last few years. We hope that reflecting on the plausibility and substantive meaning of underlying assumptions regarding different identification strategies in a particular context will lead to a better conceptualization, execution, evaluation, dissemination, and consumption of OM research. We conclude with a few thoughts that authors and reviewers may find helpful in their research as they engage in discourse related to causality.

How deadline orientation and architectural modularity influence software quality and job satisfaction

“…We focused on a cross‐sectional design to study the link among deadline orientation, architectural modularity, and software development outcomes, namely software quality and job satisfaction. Although we paid particular attention to avoid potential biases in the data collection, our approach does not allow for conclusions about causality (Mithas, Chen, Lim, & Silveira, 2022; Mithas & Krishnan, 2009).…”

Managing Product Variety to Increase Sales in Used Automotive Closed-Loop Supply Chains

“…Theoretically, discussion with company experts as well as relevant academic literature supports that the research question and associated independent variables are grounded in theory and practice (Miller et al., 2021). Additionally, the panel structure of the data and implementation of a two-way fixed effects model implies that endogeneity would be addressed by the regression model itself unless the endogenous variable was present across retail locations and time (Mithas et al., 2022; Papies et al., 2017; Rossi, 2014). Discussions with company experts identified potential unobserved explanatory variables as well as potential simultaneity concerns.…”

How will artificial intelligence and Industry 4.0 emerging technologies transform operations management?

“…Even though research in OM in general and that concerning pre‐Industry 4.0 technologies has become increasingly more empirical over time (Terwiesch, 2019; Terwiesch et al., 2020), we join calls for empirical studies on Industry 4.0 emerging technologies, with careful attention to causality and endogeneity issues (Gupta et al., 2006; Ho et al., 2017; Ketokivi & McIntosh, 2017; Roth & Rosenzweig, 2020). However, the emphasis on causality does not need to be too narrow or overemphasize a particular way of looking at causality as implicit in counterfactual or potential outcome approaches (Mithas et al, 2022a; Mithas et al, 2022b). Researchers in OM should also consider other ways of assessing causality such as qualitative comparative approaches that use a different notion of causality (based on necessary and sufficient conditions) and a set‐theoretic configurational logic leveraging Boolean algebra (Mahoney et al., 2013; Park & Mithas, 2020).…”