語系:
繁體中文
English
說明(常見問題)
回圖書館首頁
手機版館藏查詢
登入
回首頁
切換:
標籤
|
MARC模式
|
ISBD
Surrogate endpoints in clinical tria...
~
Xu, Jane (Jing).
FindBook
Google Book
Amazon
博客來
Surrogate endpoints in clinical trials: A Markov chain Monte Carlo approach.
紀錄類型:
書目-語言資料,印刷品 : Monograph/item
正題名/作者:
Surrogate endpoints in clinical trials: A Markov chain Monte Carlo approach./
作者:
Xu, Jane (Jing).
面頁冊數:
116 p.
附註:
Adviser: Scott Zeger.
Contained By:
Dissertation Abstracts International60-11B.
標題:
Biology, Biostatistics. -
電子資源:
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9950618
ISBN:
0599528117
Surrogate endpoints in clinical trials: A Markov chain Monte Carlo approach.
Xu, Jane (Jing).
Surrogate endpoints in clinical trials: A Markov chain Monte Carlo approach.
- 116 p.
Adviser: Scott Zeger.
Thesis (Ph.D.)--The Johns Hopkins University, 2000.
Longitudinal data in biomedical and public health research usually comprise repeated measures of markers of health or disease data as well as times to key clinical events. In many longitudinal studies, particularly randomized trials, the main question is whether the time to a clinical event <italic> T</italic> depends upon a treatment <italic>X</italic>. When the disease under study is chronic or with long latency periods, it can take many years and be very expensive to finish the study if we only use time-to-event data. One alternative is to use biological marker data <italic>Y</italic> as a “surrogate endpoint” for <italic>T</italic>. In this situation, models for the joint distribution of <italic>T</italic> and <italic>Y</italic> given <italic> X</italic> are valuable in assessing whether <italic>Y</italic> is a useful surrogate for <italic>T</italic> in studying <italic>X</italic>. In this thesis, I present a general model for the joint analysis of [<italic>T</italic>, <italic> Y</italic>|<italic>X</italic>] and apply the model to estimate the marginal distribution [<italic>T</italic>|<italic>X</italic>] using the relevant information in <italic>Y</italic>. I adopt a latent variable formulation like that of Fawcett and Thomas (1996) and extend it to the problem of surrogate endpoints. A Markov chain Monte Carlo algorithm is implemented for estimating parameters of interest. Several quantities of clinical relevance are proposed to determine the efficacy of a treatment. I illustrate the joint model for time to event and repeated measures with analysis of data from a randomized trial comparing risperidone to placebo for treatment of persons with schizophrenia. I extend the work to handle the possibility of multiple surrogate endpoints. The use of this methodology in validating surrogate endpoints from multi-trial study is discussed and sensitivity analyses are carried out.
ISBN: 0599528117Subjects--Topical Terms:
1018416
Biology, Biostatistics.
Surrogate endpoints in clinical trials: A Markov chain Monte Carlo approach.
LDR
:02795nam 2200277 a 45
001
929281
005
20110427
008
110427s2000 eng d
020
$a
0599528117
035
$a
(UnM)AAI9950618
035
$a
AAI9950618
040
$a
UnM
$c
UnM
100
1
$a
Xu, Jane (Jing).
$3
1252765
245
1 0
$a
Surrogate endpoints in clinical trials: A Markov chain Monte Carlo approach.
300
$a
116 p.
500
$a
Adviser: Scott Zeger.
500
$a
Source: Dissertation Abstracts International, Volume: 60-11, Section: B, page: 5291.
502
$a
Thesis (Ph.D.)--The Johns Hopkins University, 2000.
520
$a
Longitudinal data in biomedical and public health research usually comprise repeated measures of markers of health or disease data as well as times to key clinical events. In many longitudinal studies, particularly randomized trials, the main question is whether the time to a clinical event <italic> T</italic> depends upon a treatment <italic>X</italic>. When the disease under study is chronic or with long latency periods, it can take many years and be very expensive to finish the study if we only use time-to-event data. One alternative is to use biological marker data <italic>Y</italic> as a “surrogate endpoint” for <italic>T</italic>. In this situation, models for the joint distribution of <italic>T</italic> and <italic>Y</italic> given <italic> X</italic> are valuable in assessing whether <italic>Y</italic> is a useful surrogate for <italic>T</italic> in studying <italic>X</italic>. In this thesis, I present a general model for the joint analysis of [<italic>T</italic>, <italic> Y</italic>|<italic>X</italic>] and apply the model to estimate the marginal distribution [<italic>T</italic>|<italic>X</italic>] using the relevant information in <italic>Y</italic>. I adopt a latent variable formulation like that of Fawcett and Thomas (1996) and extend it to the problem of surrogate endpoints. A Markov chain Monte Carlo algorithm is implemented for estimating parameters of interest. Several quantities of clinical relevance are proposed to determine the efficacy of a treatment. I illustrate the joint model for time to event and repeated measures with analysis of data from a randomized trial comparing risperidone to placebo for treatment of persons with schizophrenia. I extend the work to handle the possibility of multiple surrogate endpoints. The use of this methodology in validating surrogate endpoints from multi-trial study is discussed and sensitivity analyses are carried out.
590
$a
School code: 0098.
650
4
$a
Biology, Biostatistics.
$3
1018416
650
4
$a
Statistics.
$3
517247
690
$a
0308
690
$a
0463
710
2 0
$a
The Johns Hopkins University.
$3
1017431
773
0
$t
Dissertation Abstracts International
$g
60-11B.
790
$a
0098
790
1 0
$a
Zeger, Scott,
$e
advisor
791
$a
Ph.D.
792
$a
2000
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9950618
筆 0 讀者評論
館藏地:
全部
電子資源
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約狀態
備註欄
附件
W9100585
電子資源
11.線上閱覽_V
電子書
EB W9100585
一般使用(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
Export
取書館
處理中
...
變更密碼
登入