Cluster‐Specific Variable Selection for Product Partition Models. (7th April 2015)

• Record Type: Journal Article
• Authors: Quintana, Fernando A.; Müller, Peter; Papoila, Ana Luisa
• Is Part Of: Scandinavian journal of statistics. Volume 42:Number 4(2015:Dec.)
• Page Start: 1065
• Page End: 1077
• Publication Date: 2015-04-07
• Subjects: clustering -- non‐parametric regression -- random partition model; Statistics -- Periodicals; 310
• DOI: 10.1111/sjos.12151
• Languages: English
• ISSNs: 0303-6898

Abstract

Abstract: We propose a random partition model that implements prediction with many candidate covariates and interactions. The model is based on a modified product partition model that includes a regression on covariates by favouring homogeneous clusters in terms of these covariates. Additionally, the model allows for a cluster‐specific choice of the covariates that are included in this evaluation of homogeneity. The variable selection is implemented by introducing a set of cluster‐specific latent indicators that include or exclude covariates. The proposed model is motivated by an application to predicting mortality in an intensive care unit in Lisboa, Portugal.