Online Program

Variable Selection for Functional Clustering (303409)

In studying the health effects of radiation, clustering techniques to identify subpopulations with densely sampled functional data are important for detecting late effects of radiation treatment. However, extraneous variables can mask the true group structure. Using a variable selection technique is particularly important in model-based clustering when little or no a priori knowledge of the structure or number of groups within the data is available, and when a large number of variables must be considered. Little work on variable selection methods for model-based clustering has been applied to functional data. We propose a greedy search algorithm to integrate variable selection into the clustering procedure, as in “Variable Selection for Model-Based Clustering” (Raftery and Dean 2006), but adapted to use with functional data. At each step in our method, two models are compared using the Akaike information criterion (AIC) corrected for small samples. Our new method successfully identifies the most important variables for clustering in two settings: a simulation study and a study examining the respiratory functions of irradiated and non-irradiated mice.