B1842
Title: Clustering of longitudinal curves via a penalized method and EM algorithm
Authors: Xin Wang - San Diego State University (United States) [presenting]
Abstract: A new method is proposed for clustering longitudinal curves. In the proposed method, clusters of mean functions are identified through a weighted concave pairwise fusion method. The EM algorithm and the alternating direction method of the multipliers algorithm are combined to estimate the group structure, mean functions and principal components simultaneously. The proposed method also allows the incorporation of the prior neighborhood information to have more meaningful groups by adding pairwise weights in the pairwise penalties. In the simulation study, the performance of the proposed method is compared to some existing clustering methods in terms of the accuracy for estimating the number of subgroups and mean functions. The results suggest that ignoring the covariance structure will have a great effect on the performance of estimating the number of groups and estimating accuracy. The effect of including pairwise weights is also explored in a spatial lattice setting to take into consideration the spatial information. The results show that incorporating spatial weights improves the performance. A real example is used to illustrate the proposed method.