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

Joint modeling and analysis of longi...

Liang, Yu.

Linked to FindBook

Google Book

Amazon

博客來

Joint modeling and analysis of longitudinal observations and observation times.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Joint modeling and analysis of longitudinal observations and observation times./
Author:	Liang, Yu.
Description:	77 p.
Notes:	Source: Dissertation Abstracts International, Volume: 67-03, Section: B, page: 1504.
Contained By:	Dissertation Abstracts International67-03B.
Subject:	Statistics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3209370
ISBN:	9780542579172

Joint modeling and analysis of longitudinal observations and observation times.
Liang, Yu.

Joint modeling and analysis of longitudinal observations and observation times. - 77 p.

Source: Dissertation Abstracts International, Volume: 67-03, Section: B, page: 1504.

Thesis (Ph.D.)--Columbia University, 2006.

In analysis of longitudinal data, it is often assumed that observation times are predetermined and the same across study subjects. Such an assumption, however, is often violated in practice. For example, in a clinical study, subjects may miss scheduled visits and/or choose to make hospital visits at his/her own times. As a result, the visiting times may be highly irregular. It is well known that if the sampling scheme is correlated with the outcome values; then the usual statistical analysis may yield bias. For longitudinal data, a number of authors have studied the case of monotone missingness, cf. Wu and Carroll (1988), Follmann and Wu (1995), Hogan and Laird (1997), Scharfstein et al. (1999); Fitzmaurice et al. (2001), among others. In recent years, nonmonotone missingness has also received much attention. Troxel et al. (1998), Deltour et al. (1999) and Preisser et al. (2000) studied the intermittent missing in which the study subjects have a common set of possible visiting time points and they may miss some of them and come back in the later visits. To incorporate possibly subject-specific follow-up process, Lin and Ying (2001), Lin, Scharfstein and Rosenheck (2004) and Sun et al. (2005) proposed to use counting process to describe arbitrary and subject-specific visiting process. In this thesis, we extend the work of Lin and Ying (2001) and propose joint modeling and analysis of longitudinal data with possibly informative observation times via shared latent variables. A two-step estimation procedure is developed for parameter estimation. We show that the resulting estimators are consistent and asymptotically normal; and that the asymptotic variance can be consistently estimated using the bootstrap method. Numerical studies indicate that the proposed approach is appropriate for practical use.

ISBN: 9780542579172Subjects--Topical Terms:

517247
Statistics.

Joint modeling and analysis of longitudinal observations and observation times.
LDR:02688nmm 2200265 4500 001 1830618
005 20070430073132.5
008 130610s2006 eng d
020 $a 9780542579172
035 $a (UnM)AAI3209370
035 $a AAI3209370
040 $a UnM $c UnM
100 1 $a Liang, Yu. $3 1907662
245 1 0 $a Joint modeling and analysis of longitudinal observations and observation times.
300 $a 77 p.
500 $a Source: Dissertation Abstracts International, Volume: 67-03, Section: B, page: 1504.
500 $a Adviser: Zhiliang Ying.
502 $a Thesis (Ph.D.)--Columbia University, 2006.
520 $a In analysis of longitudinal data, it is often assumed that observation times are predetermined and the same across study subjects. Such an assumption, however, is often violated in practice. For example, in a clinical study, subjects may miss scheduled visits and/or choose to make hospital visits at his/her own times. As a result, the visiting times may be highly irregular. It is well known that if the sampling scheme is correlated with the outcome values; then the usual statistical analysis may yield bias. For longitudinal data, a number of authors have studied the case of monotone missingness, cf. Wu and Carroll (1988), Follmann and Wu (1995), Hogan and Laird (1997), Scharfstein et al. (1999); Fitzmaurice et al. (2001), among others. In recent years, nonmonotone missingness has also received much attention. Troxel et al. (1998), Deltour et al. (1999) and Preisser et al. (2000) studied the intermittent missing in which the study subjects have a common set of possible visiting time points and they may miss some of them and come back in the later visits. To incorporate possibly subject-specific follow-up process, Lin and Ying (2001), Lin, Scharfstein and Rosenheck (2004) and Sun et al. (2005) proposed to use counting process to describe arbitrary and subject-specific visiting process. In this thesis, we extend the work of Lin and Ying (2001) and propose joint modeling and analysis of longitudinal data with possibly informative observation times via shared latent variables. A two-step estimation procedure is developed for parameter estimation. We show that the resulting estimators are consistent and asymptotically normal; and that the asymptotic variance can be consistently estimated using the bootstrap method. Numerical studies indicate that the proposed approach is appropriate for practical use.
590 $a School code: 0054.
650 4 $a Statistics. $3 517247
690 $a 0463
710 2 0 $a Columbia University. $3 571054
773 0 $t Dissertation Abstracts International $g 67-03B.
790 1 0 $a Ying, Zhiliang, $e advisor
790 $a 0054
791 $a Ph.D.
792 $a 2006
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3209370