Learning from a Service Guarantee Quasi Experiment

Abstract

The authors analyze data from a service guarantee program implemented by a midpriced hotel chain. Using a multisite regression discontinuity quasi-experimental design developed over 16 months, they control for unobserved heterogeneity among guests and treatments across hotels and develop Bayesian posterior estimates of the varying program effect for each hotel. The results contribute to theory and practice. First, they provide new insights into how service guarantee programs operate in the field. Specifically, the guarantee was more effective at hotels with a better prior service history and an easier-to-serve guest population, which is consistent with signaling arguments but does not comport with the incentive argument that guarantees actually improve service quality. Second, the results offer managers better decision rules. Specifically, the authors devise program continuation rules that are sensitive to both observed and unobserved differences across sites. In addition, they devise policies to reward hotels that exceed site-specific expectations. By controlling for observed and unobserved differences across sites, the authors show that these policies potentially reward even hotels with negative net program effects, which is useful in reducing the organizational stigma of failure. Finally, the authors identify sites that should be targeted for future program rollout by computing the odds of succeeding.