Variable Selection for Model‐Based High‐Dimensional Clustering and Its Application to Microarray Data

Publisher Website
Google Scholar
Abstract
SummaryVariable selection in high‐dimensional clustering analysis is an important yet challenging problem. In this article, we propose two methods that simultaneously separate data points into similar clusters and select informative variables that contribute to the clustering. Our methods are in the framework of penalized model‐based clustering. Unlike the classicalL1‐norm penalization, the penalty terms that we propose make use of the fact that parameters belonging to one variable should be treated as a natural “group.” Numerical results indicate that the two new methods tend to remove noninformative variables more effectively and provide better clustering results than theL1‐norm approach.

This publication has 19 references indexed in Scilit: