東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Addressing Challenges in Interval-Ce...

Gao, Xiaoming,

FindBook

Google Book

Amazon

博客來

Addressing Challenges in Interval-Censored Survival Models: Study Design and Missing Time-Dependent Covariates /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Addressing Challenges in Interval-Censored Survival Models: Study Design and Missing Time-Dependent Covariates // Xiaoming Gao.
作者:	Gao, Xiaoming,
面頁冊數:	1 electronic resource (79 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
Contained By:	Dissertations Abstracts International86-02B.
標題:	Biostatistics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31334080
ISBN:	9798383687260

Addressing Challenges in Interval-Censored Survival Models: Study Design and Missing Time-Dependent Covariates /
Gao, Xiaoming,

Addressing Challenges in Interval-Censored Survival Models: Study Design and Missing Time-Dependent Covariates /Xiaoming Gao. - 1 electronic resource (79 pages)

Source: Dissertations Abstracts International, Volume: 86-02, Section: B.

The overarching goal of this dissertation addresses the critical issues of study design and missing time-dependent covariates in the context of interval-censored survival models. Longitudinal data collected in observational cohort studies are frequently utilized to investigate associations between covariates and survival time. When studying rare diseases, the case-cohort design is often employed due to its cost-effectiveness. However, the specific event of interest is typically not observed at a precise time, but rather known to occur between two study visits. A representative case is the study of hormonal contraception (HC) and the risk of HIV acquisition (HC-HIV) where HIV infection time was only known to have occurred between the last HIV-negative and the first HIV-positive test. Existing survival analysis methods fall short in addressing these complexities. Hence, in the first part of this dissertation, we propose fitting a parametric survival model to case-cohort study data with interval-censored outcomes and both fixed and time-dependent covariates. The effectiveness of our proposed estimator was demonstrated through simulations. We applied this method to the HC-HIV study to investigate the association between specific biomarkers and the risk of HIV acquisition.The second part of the dissertation addresses a common issue in cohort studies where some visits or covariates are missed during follow-up. We propose a time-sequential method based on fully conditional specification to multiply impute missing time-dependent covariates in studies with interval-censored survival outcomes. In addition to covariates of interest, the imputation model also utilizes cumulative hazard estimated iteratively, risk status, and observance of failure in subjects' subsequent visits. Extensive simulation studies demonstrated improved performance over existing methods with reduced bias, improved efficiency, and valid inference. The proposed method was demonstrated using data from the Atherosclerosis Risk in Communities (ARIC) Study to assess the risk of hypertension with potential predictors.Finally, in the third part of the dissertation, we extend this time-sequential multiple imputation method to be applicable to case-cohort studies by incorporating inverse probability weighting. Weight is considered in both in the imputation stage and the analytical survival model. We compared the results using the proposed method with complete case analyses via simulation studies and demonstrated the method using a pseudo case-cohort study generated from the ARIC study.

English

ISBN: 9798383687260Subjects--Topical Terms:

1002712
Biostatistics.
Subjects--Index Terms:

Case-cohort study

Addressing Challenges in Interval-Censored Survival Models: Study Design and Missing Time-Dependent Covariates /
LDR:04145nmm a22004453i 4500 001 2429362
005 20250430100808.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798383687260
035 $a (MiAaPQD)AAI31334080
035 $a AAI31334080
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Gao, Xiaoming, $e author. $3 3817170
245 1 0 $a Addressing Challenges in Interval-Censored Survival Models: Study Design and Missing Time-Dependent Covariates / $c Xiaoming Gao.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (79 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
500 $a Advisors: Zou, Fei Committee members: Chen, Qingxia; Hudgens, Michael G.; Couper, David; Chen, Pai-Lien.
502 $b Dr.P.H. $c The University of North Carolina at Chapel Hill $d 2024.
520 $a The overarching goal of this dissertation addresses the critical issues of study design and missing time-dependent covariates in the context of interval-censored survival models. Longitudinal data collected in observational cohort studies are frequently utilized to investigate associations between covariates and survival time. When studying rare diseases, the case-cohort design is often employed due to its cost-effectiveness. However, the specific event of interest is typically not observed at a precise time, but rather known to occur between two study visits. A representative case is the study of hormonal contraception (HC) and the risk of HIV acquisition (HC-HIV) where HIV infection time was only known to have occurred between the last HIV-negative and the first HIV-positive test. Existing survival analysis methods fall short in addressing these complexities. Hence, in the first part of this dissertation, we propose fitting a parametric survival model to case-cohort study data with interval-censored outcomes and both fixed and time-dependent covariates. The effectiveness of our proposed estimator was demonstrated through simulations. We applied this method to the HC-HIV study to investigate the association between specific biomarkers and the risk of HIV acquisition.The second part of the dissertation addresses a common issue in cohort studies where some visits or covariates are missed during follow-up. We propose a time-sequential method based on fully conditional specification to multiply impute missing time-dependent covariates in studies with interval-censored survival outcomes. In addition to covariates of interest, the imputation model also utilizes cumulative hazard estimated iteratively, risk status, and observance of failure in subjects' subsequent visits. Extensive simulation studies demonstrated improved performance over existing methods with reduced bias, improved efficiency, and valid inference. The proposed method was demonstrated using data from the Atherosclerosis Risk in Communities (ARIC) Study to assess the risk of hypertension with potential predictors.Finally, in the third part of the dissertation, we extend this time-sequential multiple imputation method to be applicable to case-cohort studies by incorporating inverse probability weighting. Weight is considered in both in the imputation stage and the analytical survival model. We compared the results using the proposed method with complete case analyses via simulation studies and demonstrated the method using a pseudo case-cohort study generated from the ARIC study.
546 $a English
590 $a School code: 0153
650 4 $a Biostatistics. $3 1002712
650 4 $a Statistics. $3 517247
650 4 $a Epidemiology. $3 568544
653 $a Case-cohort study
653 $a Fully conditional specification
653 $a Interval-censored
653 $a Multiple imputation
653 $a Survival analysis
653 $a Time-sequential
690 $a 0308
690 $a 0766
690 $a 0463
710 2 $a The University of North Carolina at Chapel Hill. $b Biostatistics. $e degree granting institution. $3 3817171
720 1 $a Zou, Fei $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-02B.
790 $a 0153
791 $a Dr.P.H.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31334080