High dimensional multivariate mixed models for binary questionnaire data

• Published in: Journal of the Royal Statistical Society Vol. 55; no. 4; pp. 449 - 460
• Main Authors: Fieuws, Steffen, Verbeke, Geert, Boen, Filip, Delecluse, Christophe
• Format: Journal Article
• Language: English
• Published: Oxford, UK Blackwell Publishing Ltd 01-08-2006; Blackwell Publishers; Royal Statistical Society; Oxford University Press
• Series: Journal of the Royal Statistical Society Series C
• Subjects: Exercise; Generalized linear mixed model; High dimensional mixed model; Impact analysis; Item response theory; Joint model; Mathematical models; Maximum likelihood estimation; Methodology; Modeling; Multidimensional item response theory model; Multivariate analysis; Multivariate mixed model; Parametric models; Pseudolikelihood; Questionnaires; Ratio test; Self esteem; Standard error; Statistical analysis; Statistical methods; Statistical models; Studies; Surveys; Wellbeing
• ISSN: 0035-9254; 1467-9876
• DOI: 10.1111/j.1467-9876.2006.00546.x

Questionnaires that are used to measure the effect of an intervention often consist of different sets of items, each set possibly measuring another concept. Mixed models with set-specific random effects are a flexible tool to model the different sets of items jointly. However, computational problems typically arise as the number of sets increases. This is especially true when the random-effects distribution cannot be integrated out analytically, as with mixed models for binary data. A pairwise modelling strategy, in which all possible bivariate mixed models are fitted and where inference follows from pseudolikelihood theory, has been proposed as a solution. This approach has been applied to assess the effect of physical activity on psychocognitive functioning, the latter measured by a battery of questionnaires.