B1038
Title: On model-based clustering of multivariate categorical sequences
Authors: Yingying Zhang - Western Michigan Univesity (United States)
Volodymyr Melnykov - The University of Alabama (United States) [presenting]
Abstract: Modeling heterogeneous categorical data has become an important topic in categorical data analysis due to the existence of a large number of applications for such models. In the context of the analysis of categorical sequences, the existing literature on the topic primarily focuses on the analysis of univariate series. However, there is an abundance of related applications with sequences being multivariate. A novel finite mixture model is proposed, as well as the related model-based clustering approach which can effectively model heterogeneous multivariate categorical sequences and partition them into data groups. The procedure is validated on synthetic and real data, with promising results.
