Targeted Inference Involving High-Dimensional Data Using Nuisance Penalized Regression.

Targeted Inference Involving High-Dimensional Data Using Nuisance Penalized Regression.
复制标题

DOI:
10.1080/01621459.2020.1737079
复制
发表时间:
2021
影响因子:
3.7
通讯作者:
Zhang H
Zhang H
中科院分区:
数学1区
文献类型:
--
作者:
Sun Q;Zhang H

文献摘要

参考文献

相似文献

高维数据的分析在统计学中受到了越来越多的关注。在实践中,我们可能对观察到的每个变量都不感兴趣。相反,通常一些变量是特别感兴趣的,其余的变量是讨厌的。为此,我们提出了滋扰惩罚回归,不惩罚感兴趣的参数。当感兴趣的参数和滋扰参数之间的相关性可以忽略不计时,我们证明了所得到的估计量可以直接用于推断而无需任何校正。当相干性不可忽略时,我们提出了一个迭代的过程来进一步细化兴趣参数的估计,在此基础上,我们提出了一个修改的配置文件的似然统计假设检验。我们的一般结果的效用证明在三个具体的例子。数值研究进一步支持我们的方法。
Analysis of high dimensional data has received considerable and increasing attention in statistics. In practice, we may not be interested in every variable that is observed. Instead, often some of the variables are of particular interest, and the remaining variables are nuisance. To this end, we propose the nuisance penalized regression which does not penalize the parameters of interest. When the coherence between interest parameters and nuisance parameters is negligible, we show that resulting estimator can be directly used for inference without any correction. When the coherence is not negligible, we propose an iteratively procedure to further refine the estimate of interest parameters, based on which we propose a modified profile likelihood based statistic for hypothesis testing. The utilities of our general results are demonstrated in three specific examples. Numerical studies lend further support to our method.
DOI: 10.1214/17-aos1568
发表时间: 2018-04
影响因子: 4.5
作者:
Fan J;Liu H;Sun Q;Zhang T
通讯作者: Zhang T
DOI: 10.1214/16-aos1483
发表时间: 2017-12-01
影响因子: 4.5
作者:
Ning, Yang;Zhao, Tianqi;Liu, Han
通讯作者: Liu, Han
DOI: 10.1214/13-aos1098
发表时间: 2013-06-01
影响因子: 4.5
作者:
Huang J;Sun T;Ying Z;Yu Y;Zhang CH
通讯作者: Zhang CH
DOI: 10.1214/15-sts527
发表时间: 2015-11-01
影响因子: 5.7
作者:
Dezeure, Ruben;Buehlmann, Peter;Meinshausen, Nicolai
通讯作者: Meinshausen, Nicolai
DOI: 10.1002/humu.20803
发表时间: 2008-12
期刊: HUMAN MUTATION
影响因子: 3.9
作者:
Li, Chunying;Zhao, Hui;Hu, Zhibin;Liu, Zhensheng;Wang, Li-E;Gershenwald, Jeffrey E.;Prieto, Victor G.;Lee, Jeffrey E.;Duvic, Madeleine;Grimm, Elizabeth A.;Wei, Qingyi
通讯作者: Wei, Qingyi