On Partial Sufficient Dimension Reduction with Applications to Partially Linear Multi-index Models
Zhenghui Feng, Xuerong Meggie Wen, Zhou Yu, Lixing
Journal of the American Statistical Association
#002176 20131014 (published)
Partial dimension reduction is a general method to seek informative convex combinations of predictors of primary interest, which includes dimension reduction as its special case when the predictors in the remaining part are constants. In this paper, we propose a novel method to conduct partial dimension reduction estimation for predictors of primary interest without assuming that the remaining predictors are categorical. To this end, we first take the dichotomization step such that any existing approach for partial dimension reduction estimation can be employed. Then we take the expectation step to integrate over all the dichotomic predictors to identify the partial central subspace. As an example, we use the partially linear multi-index model to illustrate its applications for semiparametric modelling. Simulations and real data examples are given to illustrate our methodology.
Keywords: Partial Central Subspace; Partially Linear Multi-index Models; Partial Discretizationexpectation Estimation.

Download full text