Nonparametric estimation of conditional expectation |
| |
Authors: | Jiexiang Li Lanh Tat Tran |
| |
Institution: | 1. Department of Mathematics, College of Charleston, Robert Scott Small Room 339, Charleston, SC 29424, USA;2. Department of Mathematics, Indiana University, Bloomington, IN, USA |
| |
Abstract: | Denote the integer lattice points in the N -dimensional Euclidean space by ZN and assume that (Xi,Yi), i∈ZN is a mixing random field. Estimators of the conditional expectation r(x)=EYi|Xi=x] by nearest neighbor methods are established and investigated. The main analytical result of this study is that, under general mixing assumptions, the estimators considered are asymptotically normal. Many difficulties arise since points in higher dimensional space N?2 cannot be linearly ordered. Our result applies to many situations where parametric methods cannot be adopted with confidence. |
| |
Keywords: | primary 62G08 62E20 secondary 62M10 |
本文献已被 ScienceDirect 等数据库收录! |
|