Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/27695
Title: Overdispersion, bias and efficiency in teratology data analysis
Authors: ZHU MIN
Keywords: Overdispersion; teratology studies; beta-binomial distribution; GEEs; decoupled Gaussian estimation.
Issue Date: 28-Oct-2004
Source: ZHU MIN (2004-10-28). Overdispersion, bias and efficiency in teratology data analysis. ScholarBank@NUS Repository.
Abstract: We consider statistical methods for the analysis of teratologydata and investigate bias and efficiency of different estimatorsin presence of overdispersion. In particular, we focus on thedecoupled Gaussian method for analysis of the correlated binarydata. Both analytic and simulation studies are carried out toevaluate different models. It is found that the decoupled Gaussianmethod work especially well for joint estimation of mean andintraclass correlation parameters.Previous modelling effort usually has been conducted on viablefetuses alone. To incorporate information in the prenataldead/resorbed fetuses, we propose a new approach for jointanalysis of prenatal death/resorption and malformation. Thisapproach has several advantages: (i) it provides a convenient wayof modelling the unobserved in utero death as well asobserved defeats in risk assessment; (ii) it enables us to haveflexible choices in ordinal categorical data analysis; and (iii)we can obtain efficient statistical inference using the frameworkof the generalized estimating equations. Real data analyses areprovided for demonstrations.
URI: http://scholarbank.nus.edu.sg/handle/10635/27695
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
thesis2.pdf438.33 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

171
checked on Dec 11, 2017

Download(s)

155
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.