Measuring quality for use in incentive schemes: The case of "shrinkage" estimators

Researchers commonly "shrink" raw quality measures based on statistical criteria. This paper studies when and how this transformation's statistical properties would confer economic benefits to a utility-maximizing decisionmaker, for many asymmetric information environments. The presence of an econometric endogeneity could cause the data transformation to do either worse or better than the untransformed data. I develop the results for an application measuring teacher quality. I use data from Los Angeles to confirm the presence of the econometric endogeneity and show that the simpler raw measure would outperform the one most commonly used in teacher incentive schemes.