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/1942/7827

Title: Conditional mixed models with crossed random effects
Authors: Tibaldi, Fabian S.
Verbeke, Geert
Molenberghs, Geert
Renard, Didier
Van den Noortgate, Wirn
De Boeck, Paul
Issue Date: 2007
Publisher: BRITISH PSYCHOLOGICAL SOC
Citation: BRITISH JOURNAL OF MATHEMATICAL & STATISTICAL PSYCHOLOGY, 60. p. 351-365
Abstract: The analysis of continuous hierarchical data such as repeated measures or data from meta-analyses can be carried out by means of the linear mixed-effects model. However, in some situations this model, in its standard form, does pose computational problems. For example, when dealing with crossed random-effects models, the estimation of the variance components becomes a non-trivial task if only one observation is available for each cross-classified level. Pseudolikelihood ideas have been used in the context of binary data with standard generalized linear multilevel models. However, even in this case the problem of the estimation of the variance remains non-trivial. In this paper we first propose a method to fit a crossed random-effects model with two levels and continuous outcomes, borrowing ideas from conditional linear mixed-effects model theory. We also propose a crossed random-effects model for binary data combining ideas of conditional logistic regression with pseudolikelihood estimation. We apply this method to a case study with data coming from the field of psychometrics and study a series of items (responses) crossed with participants. A simulation study assesses the operational characteristics of the method.
Notes: Eli Lilly & Co, B-1348 Mont St Guibert, Belgium. Katholieke Univ Leuven, Louvain, Belgium. Hasselt Univ, Diepenbeek, Belgium.Tibaldi, FS, Eli Lilly & Co, Rue Granbonpre 11, B-1348 Mont St Guibert, Belgium.tibaldifa@lilly.com
URI: http://hdl.handle.net/1942/7827
DOI: 10.1348/000711006X110562
ISI #: 000250910900008
ISSN: 0007-1102
Category: A1
Type: Journal Contribution
Validation: ecoom, 2008
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Published version149 kBAdobe PDF

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