Variable Selection with Overlapping Clustering

• Activity Number: 291
• Type: Topic Contributed
• Date/Time: Tuesday, August 6, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Thierry Chekouo Tekougang*+ and Alejandro Murua
• Companies: The University of Texas MD Anderson Cancer Center and University of Montreal
• Keywords: Monte Carlo EM ; plaid model

Abstract

In high dimensional data, the number of covariates is considerably larger than the sample size. To analyze these data, we propose a new method which searchs simultaneously for the cluster structure of the observations and the informative variables. Our model for clustering and variable selection is inspired by the plaid model of Lazzeroni and Owen (2002) for biclustering. The estimation is done via the Monte Carlo EM algorithm. Applications to real data and comparisons with other methods show the advantages of our method in terms of variable selection and clustering.