Venue: The Fuqua School of Business, Duke University, 1 Towerview Drive, Durham, NC 27708-0120
Venue: The Fuqua School of Business, Duke University, 1 Towerview Drive, Durham, NC 27708-0120
This session presents three method-intensive applications in health that are challenging due to selection biases and endogeneity biases and also outcomes that follow non-linear models. The first talk presents a general overview of marginal and incremental effects in parametric nonlinear models with endogenous regressors. It also proposes a consistent estimator for such marginal and incremental effects and the correct formulation of the asymptotic standard error of the estimator. It then illustrates the application of this estimator to the analysis of the effect of substance abuse on the probability of full-time employment. The second paper discusses Bayesian estimation of an ordered probit model with endogenous selection in the context of the effect of dental insurance on the utilization of general dental services. The third paper entirely focuses on Medicare health plan choices for the elderly and presents a new model based on screening plan choices.
| Title | Presenter | Discussant |
|---|---|---|
| Medicare Beneficiaries' Choice of Medicare Health Plans - A Choice-with-Screening Model |
Qian Li (Indiana University) | Willard Manning (University of Chicago ) |
| Parametric Regression and Health Policy Analysis: Survey-Based Estimation in the Presence of Endogeneity |
Joseph V. Terza (University of Florida) | Willard Manning (University of Chicago ) |
| A Bayesian Analysis of the OPES Model with a Non-parametric Component: Application to Dental Insurance and Dental Care |
Pravin K. Trivedi (Indiana University) | Frank Windmeijer (University of Bristol) |