Untitled
Language
en
Article de revue
This item was published in
Statistica Sinica. 2010, vol. 20, n° 2, p. 513-536
Taipei : Institute of Statistical Science, Academia Sinica
English Abstract
Most of the common estimation methods for sample selection models rely heavily on parametric and normality assumptions. We consider in this paper a multivariate semiparametric sample selection model and develop a geometric ...Read more >
Most of the common estimation methods for sample selection models rely heavily on parametric and normality assumptions. We consider in this paper a multivariate semiparametric sample selection model and develop a geometric approach to the estimation of the slope vectors in the outcome equation and in the selection equation. Contrary to most existing methods, we deal symmetrically with both slope vectors. Moreover, the estimation method is link-free and distributionfree. It works in two main steps: a multivariate sliced inverse regression step, and a canonical analysis step. We establish pn-consistency and asymptotic normality of the estimates. We describe how to estimate the observation and selection link functions. The theory is illustrated with a simulation study.Read less <
English Keywords
Sliced Inverse Regression (SIR)
Multivariate SIR
Canonical Analysis
Semiparametric Regression Models
Eigen-decomposition
Origin
Hal imported