Model Selection for Poisson Regression via Association Rules Analysis

• Activity Number: 366
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Pannapa Changpetch*+ and Dennis Kon-Jin Lin
• Companies: Bentley University and The Pennsylvania State University
• Keywords: Poisson regression ; Association rules analysis ; Interaction effects

Abstract

In this research, we propose a novel approach for a Poisson regression model selection procedure: specifically, we apply association rules analysis to identifying potential interactions for Poisson regression modeling. Interaction effects are very common in reality, but has received little attention in Poisson regression literature. This is especially true for higher-order interactions. Here, we develop a model selection framework to address this problem. Specifically, we focus on building an optimal Poisson regression model by (1) finding (low- and high-order) interactions among the input variables via association rules analysis; (2) selecting the potential interactions; (3) converting these potential interactions into new dummy variables; and (4) performing variable selections among all the input variables and the newly created dummy variables (interactions) to build up the optimal Poisson regression model. Our model selection procedure is the first approach to provide a global search for potential interactions and establish the optimal combination of main effects and interaction effects in the Poisson regression model.