A0612
Title: A generalized Heckman model with varying sample selection bias and dispersion parameters
Authors: Wagner Barreto-Souza - University College Dublin (Ireland) [presenting]
Fernando Souza - Universidade Federal de Vicosa (Brazil)
Marc Genton - KAUST (Saudi Arabia)
Abstract: A generalization of the Heckman sample selection model is proposed by allowing the sample selection bias and dispersion parameters to depend on covariates. It is shown that the non-robustness of the Heckman model may be due to the assumption of the constant sample selection bias parameter rather than the normality assumption. The proposed methodology allows understanding which covariates are important to explain the sample selection bias phenomenon rather than only forming conclusions about its presence. Further, the approach may attenuate the non-identifiability and multicollinearity problems faced by the existing sample selection models. The inferential aspects of the maximum likelihood estimators (MLEs) for the proposed generalized Heckman model are explored. More specifically, it is shown that this model satisfies some regularity conditions such that it ensures consistency and asymptotic normality of the MLEs. Proper score residuals for sample selection models are provided, and model adequacy is addressed. Simulated results are presented to check the finite-sample behavior of the estimators and to verify the consequences of not considering varying sample selection bias and dispersion parameters. It is shown that the normal assumption for analyzing medical expenditure data is suitable and that the conclusions drawn using the approach are coherent with findings from prior literature.
