Addressing endogeneity can be a challenging task given the different sources of endogeneity and their impacts on empirical results. While premier business journals typically expect authors to rigorously address endogeneity, this expectation is relatively new to many Operations Management (OM) scholars, as exemplified by a recent editorial in Journal of Operations Management that calls for more rigorous treatment for endogeneity. This study serves two purposes. First, we summarize recent OM literature with respect to the treatment for endogeneity by reviewing studies published in leading OM journals between 2012 and 2017. The review provides evidence that endogeneity problems have received increasing attention from OM scholars. However, we also find some common problems that may render the chosen techniques for addressing endogeneity less effective and potentially lead to biased analysis results. Second, since instrumental variable regression is the most prevalent technique for dealing with endogeneity in the OM literature according to our review, we provide an empirical illustration tailored to OM researchers for using instrumental variable regression in the post‐design (data analysis) phase. Using variables from a publicly available healthcare dataset, our analysis sheds light on the importance of examining instruments' quality and triangulating results based on more than one test/estimator.

Staffing decisions are crucial for retailers since staffing levels affect store performance and labor‐related expenses constitute one of the largest components of retailers’ operating costs. With the goal of improving staffing decisions and store performance, we develop a labor‐planning framework using proprietary data from an apparel retail chain. First, we propose a sales response function based on labor adequacy (the labor to traffic ratio) that exhibits variable elasticity of substitution between traffic and labor. When compared to a frequently used function with constant elasticity of substitution, our proposed function exploits information content from data more effectively and better predicts sales under extreme labor/traffic conditions. We use the validated sales response function to develop a data‐driven staffing heuristic that incorporates the prediction loss function and uses past traffic to predict optimal labor. In counterfactual experimentation, we show that profits achieved by our heuristic are within 0.5% of the optimal (attainable if perfect traffic information was available) under stable traffic conditions, and within 2.5% of the optimal under extreme traffic variability. We conclude by discussing implications of our findings for researchers and practitioners.

A potential answer to retailer's shelf out‐of‐stocks (OOS), where the item is in the store but customers cannot find it, is to employ third‐party service providers to execute audits and corrections. However, given the nontrivial cost of executing external audits, it is still necessary to assess whether external audits are capable of reducing shelf‐OOS, whether they can be performed in an economical way, and whether the benefits from the audits translate into higher sales. In an effort to address these questions, we partnered with a product manufacturer and a retail service provider and conducted a field experiment in a national retailer's store set. We used transactional data to detect abnormal operations and respond to possible shelf‐OOS by sending auditors to correct empty shelves and incorrect inventory records. At the conclusion of the experiment, we found that Stock Keeping Units in the treatment group were less likely to have shelf‐OOS and inventory record inaccuracies, and that our intervention had a positive effect on sales. Furthermore, we found that the external audit initiative is economically viable since these improvements required low auditing efforts after a transitional period, and in steady state the cost of running the program is a small fraction of the benefits it generates. We discuss the limitations of our study and the implications of our findings for researchers and practitioners.

Inventory record inaccuracy (IRI) is a pervasive problem in retailing and causes non-trivial profit loss. In response to retailers' interest in identifying antecedents and consequences of IRI, we present a study that comprises multiple modeling initiatives. We first develop a dynamic simulation model to compare and contrast impacts of different operational errors in a continuous (Q, R) inventory system through a fullfactorial experimental design. While backroom and shelf shrinkage are found to be predominant drivers of IRI, the other three errors related to recording and shelving have negligible impacts on IRI. Next, we empirically assess the relationships between labor availability and IRI using longitudinal data from five stores in a global retail chain. After deriving a robust measure of IRI through Bayesian computation and estimating panel data models, we find strong evidence that full-time labor reduces IRI whereas part-time labor fails to alleviate it. Further, we articulate the reinforcing relationships between labor and IRI by formally assessing the gain of the feedback loop based on our empirical findings and analyzing immediate, intermediate, and long-term impacts of IRI on labor availability. The feedback modeling effort not only integrates findings from simulation and econometric analysis but also structurally explores the impacts of current practices. We conclude by discussing implications of our findings for practitioners and researchers.

R etail inventories have been consistently dropping, relative to sales, since the 1990s. Whether these lean inventory developments translate to better retailer operational performance is still an open question. We empirically examine associations between inventory leanness and operational efficiency for a sample of public US retailers from 2000 to 2013. Via a stochastic frontier analysis that accounts for retailer heterogeneity and time parameters, we find support for the hypothesis that operational efficiency has an inverted U-shape relationship with inventory leanness, suggesting an optimal inventory leanness level beyond which retailer operational efficiency degrades. This relationship, however, is heavily moderated by firm size and demand uncertainty. The former reflects a retailer's abilities to exploit economies of scale and scope, whereas the latter reflects the unpredictability in a firm's operating environment. Our evidence suggests that when increasing inventory leanness, small retailers exhibit efficiency degradation, whereas larger retailers are likely to exhibit efficiency improvement, with diminishing returns. We also find that under high demand uncertainty, being less lean is associated with higher operational efficiency, regardless of firm size. The findings show that depending on firm size and demand uncertainty, retail managers should take special care when pursuing inventory leanness. As part of post hoc robustness tests, we assess how different retail categories vary in their operational efficiency scores and conduct interviews with retail executives who further ground our econometric investigation and point to more nuanced moderators for future studies. We conclude by discussing the implications of our industry model estimation for managers and researchers.