Problem definition: Misconduct, such as theft, is a major problem in operational settings, and staffing decisions can either amplify or mitigate this problem as workers influence their peers' behavior. Peers are known to influence coworker productivity and likely also affect counterproductive behaviors. Academic/practical relevance: Many studies have shown how mechanisms such as helping, knowledge transfer, teaching, and social pressure generate productivity peer effects in service and other settings. Yet few papers empirically examine these effects in counterproductive behaviors. We argue that while the same mechanisms driving productivity spillovers also generate peer effects in misconduct, an additional effect - strategic peer response - reflects how coworkers, under managerial monitoring, adjust misconduct in response to peers' daily behavior. An additional contribution of this paper is to identify the effect of peers on operational performance in a firm setting. Methodology: We use transaction and theft data from 83,153 servers at 1,049 restaurants across 46 states in the United States. We employ instrumental variable (IV) models to account for both reflection problems and correlated error terms in same-day peer theft. We use Monte Carlo simulations to present how biases identified by a combination of ordinary least squares (OLS) and IV models suggest that managerial oversight might generate negative correlation in the same-day error terms of peers that reflects strategic peer responses. Results: Our results show that although servers are more likely to steal when working with high-theft peers, they steal less as peers steal more on a given day. We also show that this negative correlation in daily peer theft is higher under an information technology system that increases managerial oversight by reporting likely theft to managers. Importantly, we demonstrate how reflection effects can significantly amplify even small peer-effect coefficients to have large organizational implications. Our parameter estimates indicate that doubling a single worker's average theft amount will increase total theft in an average restaurant by 76%. Doubling all workers' theft amounts increases totals by 550%. Finally, we show that the positive peer effect from high-theft coworkers only exists for new workers in their first three to five months on the job, consistent with imprinting mechanisms that include knowledge transfer and norms. Managerial implications: The results show that the costs of employing unethical workers is higher than the direct cost of those workers' misconduct because their behavior spills over into coworkers' actions and amplifies through reflection effects. Yet our results also suggest that this contagion can be mitigated by managerial oversight. So long as there is sufficient monitoring of misconduct, workers will strategically limit such behavior in response to peers. © 2020 INFORMS.
