Please use this identifier to cite or link to this item:
Title: Flexible Model Strategies and Sensitivity Analysis Tools for Non-Monotone Incomplete Categorical Data
Authors: JANSEN, Ivy 
Advisors: MOLENBERGHS, Geert
Issue Date: 2005
Abstract: Throughout this thesis, it has become evident that a variety of approaches is possible, when analyzing incomplete longitudinal data. First and foremost, an alternative was given for the frequently used but highly restrictive complete case analysis and last observation carried forward analysis. While the latter assume the data to be missing completely at random, the assumption of missing at random is sufficient for the linear mixed models, when the data are continuous, and for the generalized linear mixed models in the random-effects approach, or the weighted generalized estimating equations in the marginal model context, when the data are of the binary type. All methods can be easily performed with the currently available statistical analysis software. With the analyses of data in different scientific fields, we hope these methods will achieve more popularity in the near future. Within the fast growing field of statistical genetics, where missing data are very common, much simpler methods are used more frequently (Jansen et al., 2002, 2005d). However, although these data are not necessarily of the longitudinal type, the GEE method has already been used.
Document URI:
Category: T1
Type: Theses and Dissertations
Appears in Collections:PhD theses
Research publications

Files in This Item:
File Description SizeFormat 
doct_Ivy Janssen.pdf3.26 MBAdobe PDFView/Open
Show full item record

Page view(s)

checked on May 23, 2022


checked on May 23, 2022

Google ScholarTM


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