高维回归中协变量的逐步选择
统计方法学
2017-10-06 v4
摘要
给定数据y(n)和p(n)个协变量x(n)，线性回归中的一个问题是决定包含哪些协变量（如果有）。关于此问题已有许多文章，但都基于数据的随机模型。本文给出了一种似乎全新的方法，其不需要任何形式的模型。它在概念和算法上简单，并且一致性结果可在适当假设下得到证明。
引用
@article{arxiv.1610.05131,
title = {Stepwise Choice of Covariates in High Dimensional Regression},
author = {Laurie Davies},
journal= {arXiv preprint arXiv:1610.05131},
year = {2017}
}
备注
This is a revised version of 1610.05131. It contains some results on false postives, an analysis of the birthday data also analysed in "Bayesian Data Analysis" (Chapman & Hall/CRC Texts in Statistical Science) and an application to the construction of dependency graphs. 38 pages and one figure