We use a randomized experiment and a structural model to test whether monitoring and financial incentives can reduce teacher absence and increase learning in rural India.In treatment schools, teachers' attendance was monitored daily using cameras, and their salaries were made a nonlinear function of attendance. Absenteeism by teachers fell by 21 percentage points relative to the control group, and children's test scores increased by 0.17 standard deviations. We estimate a structural dynamic labor supply model and find that teachers responded strongly to the financial incentives, and that this alone can explain the difference between the two groups. Our model is used to compute cost-minimizing compensation policies. * This project is a collaborative exercise involving many people. Foremost, we are deeply indebted to Seva Mandir, and especially to Neelima Khetan and Priyanka Singh, who made this evaluation possible. We thank Ritwik Sakar and Ashwin Vasan for their excellent work coordinating the fieldwork. Greg Fischer, Shehla Imran, Callie Scott, Konrad Menzel, and Kudzaishe Takavarasha provided superb research assistance. For their helpful comments, we thank referees, Abhijit Banerjee, Rachel Glennerster, Michael Kremer and Sendhil Mullainathan. We owe a special thank to the referees, who made substantial suggestions that considerably improved the paper. For financial support, we thank the John D. and Catherine T. MacArthur Foundation.

We use employee-level panel data from a single firm to explore the possibility that individuals may select insurance coverage in part based on their anticipated behavioral (“moral hazard”) response to insurance, a phenomenon we label “selection on moral hazard.” Using a model of plan choice and medical utilization, we present evidence of heterogeneous moral hazard as well as selection on it, and explore some of its implications. For example, we show that, at least in our context, abstracting from selection on moral hazard could lead to over-estimates of the spending reduction associated with introducing a high-deductible health insurance option.

We discuss the identification and estimation of discrete games of complete information. Following Reiss (1990, 1991), a discrete game is a generalization of a standard discrete choice model where utility depends on the actions of other players. Using recent algorithms to compute all of the Nash equilibria to a game, we propose simulation-based estimators for static, discrete games. With appropriate exclusion restrictions about how covariates enter into payoffs and influence equilibrium selection, the model is identified with only weak parametric assumptions. Monte Carlo evidence demonstrates that the estimator can perform well in moderately-sized samples. As an application, we study the strategic decision of firms in spatially-separated markets to establish a presence on the Internet.

We survey and apply several techniques from the statistical and computer science literature to the problem of demand estimation. To improve out-of-sample prediction accuracy, we propose a method of combining the underlying models via linear regression. Our method is robust to a large number of regressors; scales easily to very large data sets; combines model selection and estimation; and can flexibly approximate arbitrary non-linear functions. We illustrate our method using a standard scanner panel data set and find that our estimates are considerably more accurate in out-of-sample predictions of demand than some commonly used alternatives.