Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1149653 | Journal of Statistical Planning and Inference | 2012 | 12 Pages |
Abstract
In this paper we consider a semiparametric regression model involving a d-dimensional quantitative explanatory variable X and including a dimension reduction of X via an index βâ²X. In this model, the main goal is to estimate the Euclidean parameter β and to predict the real response variable Y conditionally to X. Our approach is based on sliced inverse regression (SIR) method and optimal quantization in Lp-norm. We obtain the convergence of the proposed estimators of β and of the conditional distribution. Simulation studies show the good numerical behavior of the proposed estimators for finite sample size.
Related Topics
Physical Sciences and Engineering
Mathematics
Applied Mathematics
Authors
Romain Azaïs, Anne Gégout-Petit, Jérôme Saracco,