比例风险回归中存在似然单调性的推理

IF 1.4 3区数学 Q2 STATISTICS & PROBABILITY

Statistica Neerlandica Pub Date : 2023-01-20 DOI:10.1111/stan.12287

J. Kolassa, Juan Zhang

{"title":"比例风险回归中存在似然单调性的推理","authors":"J. Kolassa, Juan Zhang","doi":"10.1111/stan.12287","DOIUrl":null,"url":null,"abstract":"Proportional hazards are often used to model event time data subject to censoring. Samples involving discrete covariates with strong effects can lead to infinite maximum partial likelihood estimates. A methodology is presented for eliminating nuisance parameters estimated at infinity using approximate conditional inference. Of primary interest is testing in cases in which the parameter of primary interest has a finite estimate, but in which other parameters are estimated at infinity.","PeriodicalId":51178,"journal":{"name":"Statistica Neerlandica","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2023-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Inference in the presence of likelihood monotonicity for proportional hazards regression\",\"authors\":\"J. Kolassa, Juan Zhang\",\"doi\":\"10.1111/stan.12287\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Proportional hazards are often used to model event time data subject to censoring. Samples involving discrete covariates with strong effects can lead to infinite maximum partial likelihood estimates. A methodology is presented for eliminating nuisance parameters estimated at infinity using approximate conditional inference. Of primary interest is testing in cases in which the parameter of primary interest has a finite estimate, but in which other parameters are estimated at infinity.\",\"PeriodicalId\":51178,\"journal\":{\"name\":\"Statistica Neerlandica\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2023-01-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Statistica Neerlandica\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://doi.org/10.1111/stan.12287\",\"RegionNum\":3,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"STATISTICS & PROBABILITY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Statistica Neerlandica","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1111/stan.12287","RegionNum":3,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"STATISTICS & PROBABILITY","Score":null,"Total":0}

引用次数: 0

摘要

比例风险常用于对事件时间数据进行建模。涉及具有强影响的离散协变量的样本可能导致无限最大部分似然估计。提出了一种利用近似条件推理消除无穷远处估计的干扰参数的方法。我们最感兴趣的是在主要感兴趣的参数有一个有限的估计，而其他参数的估计是无穷大的情况下进行检验。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Inference in the presence of likelihood monotonicity for proportional hazards regression

Proportional hazards are often used to model event time data subject to censoring. Samples involving discrete covariates with strong effects can lead to infinite maximum partial likelihood estimates. A methodology is presented for eliminating nuisance parameters estimated at infinity using approximate conditional inference. Of primary interest is testing in cases in which the parameter of primary interest has a finite estimate, but in which other parameters are estimated at infinity.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Statistica Neerlandica 数学-统计学与概率论

CiteScore

2.60

自引率

6.70%

发文量

审稿时长

>12 weeks

期刊介绍： Statistica Neerlandica has been the journal of the Netherlands Society for Statistics and Operations Research since 1946. It covers all areas of statistics, from theoretical to applied, with a special emphasis on mathematical statistics, statistics for the behavioural sciences and biostatistics. This wide scope is reflected by the expertise of the journal’s editors representing these areas. The diverse editorial board is committed to a fast and fair reviewing process, and will judge submissions on quality, correctness, relevance and originality. Statistica Neerlandica encourages transparency and reproducibility, and offers online resources to make data, code, simulation results and other additional materials publicly available.