群集多變量競爭風險資料及高維度共變量分析;Analysis of Clustered Multivariate Competing Risks Data with High-Dimensional Covariates

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/78619

Title:	群集多變量競爭風險資料及高維度共變量分析;Analysis of Clustered Multivariate Competing Risks Data with High-Dimensional Covariates
Authors:	江村剛志
Contributors:	國立中央大學統計研究所
Keywords:	Survival analysis;Gene expression;Cox model;Censoring;Copula;Survival analysis;Gene expression;Cox model;Censoring;Copula
Date:	2018-12-19
Issue Date:	2018-12-20 12:07:41 (UTC+8)
Publisher:	科技部
Abstract:	本研究計畫的目標為建立可同時處理群集多變量存活時間及高維度共變量之競爭風險分析方法。現今既有的方法大部份都專注於處理二維度競爭風險，因此無法處理現實醫學研究中複雜的存活資料。此為期三年的計畫，目標為一年發展一種統計方法來分析共三種不同的資料結構，每種資料結構均須要使用在過去文獻中未曾被使用過的copula之應用，此外，本計畫也包含每年處理高維度共變量之議題 ;The objective of my research proposal is to create new competing risks analysis methods that can deal with clustered multivariate survival times together with high-dimensional covariates. Existing methodologies are mostly focused on two dimensional competing risks and are not enough to deal with complex survival data obtained from real medical studies. This 3-year project has a plan to develop statistical methods for analyzing 3 different types of data structures, one type for each year. Each data structure needs novel applications of copulas that have never been considered in the literature. In addition, every year handles the issue of high-dimensional covariates that will also be discussed in this proposal.
Relation:	財團法人國家實驗研究院科技政策研究與資訊中心
Appears in Collections:	[Graduate Institute of Statistics] Research Project

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	301	View/Open

社群 sharing

Loading...