東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

New approaches for the analysis of m...

Fu, Pingfu.

Linked to FindBook

Google Book

Amazon

博客來

New approaches for the analysis of multivariate time-to-event data using generalized linear models.

Record Type:	Electronic resources : Monograph/item
Title/Author:	New approaches for the analysis of multivariate time-to-event data using generalized linear models./
Author:	Fu, Pingfu.
Description:	100 p.
Notes:	Source: Dissertation Abstracts International, Volume: 62-11, Section: B, page: 4880.
Contained By:	Dissertation Abstracts International62-11B.
Subject:	Biology, Biostatistics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3034620
ISBN:	0493473688

New approaches for the analysis of multivariate time-to-event data using generalized linear models.
Fu, Pingfu.

New approaches for the analysis of multivariate time-to-event data using generalized linear models. - 100 p.

Source: Dissertation Abstracts International, Volume: 62-11, Section: B, page: 4880.

Thesis (Ph.D.)--Case Western Reserve University (Health Sciences), 2001.

One branch of statistics is survival analysis, or more accurately, the analysis of time-to-event data. A basic example of survival data is time to death, which forms the basis of survival analysis. This area is characterized by the dynamic temporal aspect, making modeling via the hazard function useful, and by the special patterns of incompleteness of observation, called censoring.

ISBN: 0493473688Subjects--Topical Terms:

1018416
Biology, Biostatistics.

New approaches for the analysis of multivariate time-to-event data using generalized linear models.
LDR:02985nmm 2200301 4500 001 1865162
005 20041216142218.5
008 130614s2001 eng d
020 $a 0493473688
035 $a (UnM)AAI3034620
035 $a AAI3034620
040 $a UnM $c UnM
100 1 $a Fu, Pingfu. $3 1952622
245 1 0 $a New approaches for the analysis of multivariate time-to-event data using generalized linear models.
300 $a 100 p.
500 $a Source: Dissertation Abstracts International, Volume: 62-11, Section: B, page: 4880.
500 $a Adviser: J. Sunil Rao.
502 $a Thesis (Ph.D.)--Case Western Reserve University (Health Sciences), 2001.
520 $a One branch of statistics is survival analysis, or more accurately, the analysis of time-to-event data. A basic example of survival data is time to death, which forms the basis of survival analysis. This area is characterized by the dynamic temporal aspect, making modeling via the hazard function useful, and by the special patterns of incompleteness of observation, called censoring.
520 $a One very active research area involves multivariate time-to-event data. The analysis of this type of data is complicated by the dependence of survival times within each cluster.
520 $a Our research work in this area consists of two pieces. In the first part, we make use the well-known connection between the survival data and Poisson regression (Aitkin-Clayton model) and apply the clustering sampling technique (Rao-Scott approach) to the multivariate survival data. We fit the model assuming an independence correlation structure, and adjust the variance of the parameter estimates by a design effect approach adopted from cluster sampling. In order to test our design effect approach, we generated correlated Weibull variates and applied our method to them in our simulation study.
520 $a In the second part of the thesis, we introduce a time-dependent frailty model for both the single-level and multiple-level of clustering model using a connection between our models with generalized linear mixed models. We proposed an iterative algorithm to estimate all the parameters based on a score equation and a penalized score equation. We also prove the consistency and asymptotic properties of our estimates. Variances and possible biases of parameter estimates are further examined by grouped jackknife approach. Clinically, the existence of the time-dependent frailty effect may guide researchers their in treatment decisions. The method is applied to the randomized clinic study of chronic granulomatous disease (CGD) in which patients were randomized to placebo and gamma interferon, and simulated datasets in order to check the validity of our method.
590 $a School code: 0499.
650 4 $a Biology, Biostatistics. $3 1018416
690 $a 0308
710 2 0 $a Case Western Reserve University (Health Sciences). $3 1250782
773 0 $t Dissertation Abstracts International $g 62-11B.
790 1 0 $a Rao, J. Sunil, $e advisor
790 $a 0499
791 $a Ph.D.
792 $a 2001
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3034620