www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/22840

Title: Local influence diagnostics for hierarchical count data models with overdispersion and excess zeros
Authors: Rakhmawati, Trias Wahyuni
Molenberghs, Geert
Verbeke, Geert
Faes, Christel
Issue Date: 2016
Publisher: WILEY-BLACKWELL
Citation: BIOMETRICAL JOURNAL, 58(6), p. 1390-1408
Abstract: We consider models for hierarchical count data, subject to overdispersion and/or excess zeros. Molenberghs etal. () and Molenberghs etal. () extend the Poisson-normal generalized linear-mixed model by including gamma random effects to accommodate overdispersion. Excess zeros are handled using either a zero-inflation or a hurdle component. These models were studied by Kassahun etal. (). While flexible, they are quite elaborate in parametric specification and therefore model assessment is imperative. We derive local influence measures to detect and examine influential subjects, that is subjects who have undue influence on either the fit of the model as a whole, or on specific important sub-vectors of the parameter vector. The latter include the fixed effects for the Poisson and for the excess-zeros components, the variance components for the normal random effects, and the parameters describing gamma random effects, included to accommodate overdispersion. Interpretable influence components are derived. The method is applied to data from a longitudinal clinical trial involving patients with epileptic seizures. Even though the data were extensively analyzed in earlier work, the insight gained from the proposed diagnostics, statistically and clinically, is considerable. Possibly, a small but important subgroup of patients has been identified.
Notes: [Rakhmawati, Trias Wahyuni; Molenberghs, Geert; Verbeke, Geert; Faes, Christel] Univ Hasselt, I BioStat, Martelarenlaan 42, B-3500 Hasselt, Belgium. [Molenberghs, Geert; Verbeke, Geert; Faes, Christel] Katholieke Univ Leuven, I BioStat, Kapucijnenvoer 35, B-3000 Leuven, Belgium.
URI: http://hdl.handle.net/1942/22840
DOI: 10.1002/bimj.201500162
ISI #: 000387148100008
ISSN: 0323-3847
Category: A1
Type: Journal Contribution
Validation: ecoom, 2017
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Published version630.18 kBAdobe PDF
Peer-reviewed author version2.88 MBAdobe PDF

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