Please use this identifier to cite or link to this item:
Type: Conference paper
Title: Modeling individual differences with Dirichlet processes
Author: Navarro, D.
Griffiths, T.
Steyvers, M.
Lee, M.
Citation: XXVII Annual Conference of the Cognitive Science Society / B. G. Bara, L. W. Barsalou & M. Bucciarelli (eds.): pp.1594-1599
Publisher: Lawrence Erlbaum Associates, Inc.
Publisher Place: New Jersey, USA
Issue Date: 2005
ISBN: 0976831813
Conference Name: Cognitive Science Society. Annual Conference (27th : 2005 : Stresa, Italy)
Statement of
Daniel J. Navarro, Thomas L. Griffiths, Mark Steyvers, Michael D. Lee
Abstract: We introduce a Bayesian framework for modeling individual differences, in which subjects are assumed to belong to one of a potentially infinite number of groups. In this model, the groups observed in any particular data set are not viewed as a fixed set that fully explain the variation between individuals, but rather as representatives of a latent, arbitrarily rich structure. As more people are seen, the number of observed groups is allowed to grow, as more details about the individual differences are revealed. We use the Dirichlet process – a distribution widely used in nonparametric Bayesian statistics – to define a prior for the model, allowing us to learn flexible parameter distributions without overfitting the data, or requiring the complex computations typically required for determining the dimensionality of a model. As an initial demonstration of the approach, we present an application of the method to categorization data.
Rights: © the authors
RMID: 0020052412
Appears in Collections:Psychology publications
Environment Institute publications

Files in This Item:
File Description SizeFormat 
hdl_28882.pdfPublished version403.88 kBAdobe PDFView/Open

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