Conference Proceedings


Isobel Claire Gormley
Damien McParland


Computer Science

clinical trial data models social and behavioral sciences computer applications statistics and computing statistics programs self assessment clustering clinical assessment

Clustering Ordinal Data via Latent Variable Models (2011)

Abstract Item response modelling is a well established method for analysing ordinal response data. Ordinal data are typically collected as responses to a numberof questions or items. The observed data can be viewed as discrete versions of anunderlying latent Gaussian variable. Item response models assume that this latentvariable (and therefore the observed ordinal response) is a function of both respondent specific and item specific parameters. However, item response models assumea homogeneous population in that the item specific parameters are assumed to bethe same for all respondents. Often a population is heterogeneous and clusters ofrespondents exist; members of different clusters may view the items differently. Amixture of item response models is developed to provide clustering capabilities inthe context of ordinal response data. The model is estimated within the Bayesianparadigm and is illustrated through an application to an ordinal response data setresulting from a clinical trial involving self-assessment of arthritis.
Collections Ireland -> University College Dublin -> College of Science
Ireland -> University College Dublin -> Mathematics and Statistics Research Collection
Ireland -> University College Dublin -> School of Mathematics and Statistics

Full list of authors on original publication

Isobel Claire Gormley, Damien McParland

Experts in our system

Isobel Claire Gormley
University College Dublin
Total Publications: 25
Damien McParland
University College Dublin
Total Publications: 9