A0242
Title: Clustered coefficient regression models for Poisson process with an application to seasonal warranty claim data
Authors: Xin Wang - San Diego State University (United States) [presenting]
Xin Zhang - Independent researcher (United States)
Zhengyuan Zhu - Iowa State University (United States)
Abstract: Motivated by a product warranty claims data set, clustered coefficient regression models are proposed in a non-homogeneous Poisson process for recurrent event data. The proposed method referred to as CLUPP, can simultaneously estimate the group structure and parameters. The proposed method uses a penalized regression approach to identify the group structure. Numerical studies show that the proposed approach can identify the group structure well and outperforms traditional methods such as hierarchical clustering and $K$-means. Theoretical properties are also established, which show that the proposed estimators can converge to true parameters in high probability. The proposed methods are ultimately applied to the product warranty claims data set, achieving better prediction than the state-of-the-art methods.
