Contributions to Structural Modeling and Estimation

The first chapter of my thesis develops and estimates a dynamic structural partial equilibrium model of schooling and work decisions.  The estimated model explicitly accounts for the simultaneous choice of enrolling in school and working.  It also allows for endogenous leisure choices, intertemporal nonseparabilities in preferences, aggregate skill specific productivity shocks, aggregate consumption price effects, and individual heterogeneity.  Times spent on schooling, working, and leisure are treated as continuous choice variables.  The estimated model is solved and two counterfactual simulation exercises are performed.  The first is the case where a subsidy is given to individuals who enroll in school and do not participate in the labor market.  The second is the case where the demands of the school curriculum are increased so that a young man enrolled in school necessarily spends more time studying.   The conclusion is that the latter policy is more effective in enhancing educational achievements and future wages. The second chapter of my thesis develops a semiparametric estimator for a dynamic nonlinear single index panel data model.  Flexibility of the model is achieved by assuming that the index function is unknown.  Flexibility in individual heterogeneity is achieved by assuming that the individual effect is an unknown function of some observable random variable.  The paper proposes an algorithm that estimates each of the finite and infinite dimensional parameters. In particular, the full data generating process is estimated.  This is important if the predicted outcomes are used as plug-in estimators, as in the multistage estimation of dynamic structural models. The final chapter of my thesis develops a powerful new algorithm to solve single object first price auctions where bidders draw independent private values from heterogeneous distributions.  The algorithm allows for the scenario in which groups of symmetric and asymmetric bidders may collude, and for the auctioneer to set a reserve price.  The paper also provides operational univariate quadratures to evaluate the probabilities of winning as well as the expected revenues for the bidders and the auctioneer.  The expected revenue function is used to the compute optimal reserve under asymmetric environments.