Dynamic Logistic Regression and Dynamic Model Averaging for Binary Classification

• Activity Number: 223
• Type: Topic Contributed
• Date/Time: Monday, August 1, 2011 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Tyler McCormick*+ and Adrian Raftery and David Madigan and Randall Burd
• Companies: University of Washington and University of Washington and Columbia University and Children's National Medical Center
• Keywords: Bayesian model averaging ; Binary classification ; Confidentiality ; Hidden Markov model ; Laparoscopic surgery ; Markov chain

Abstract

We propose an online binary classification procedure for cases when there is uncertainty about the model to use and when parameters within a model change over time. We account for model uncertainty through Dynamic Model Averaging (DMA), a dynamic extension of Bayesian Model Averaging (BMA) in which posterior model probabilities are also allowed to change with time. We do this by applying a state-space model to the parameters of each model and a Markov chain model to the data-generating model, allowing the "correct'' model to change over time. Our method accommodates different levels of change in the data-generating mechanism by calibrating a "forgetting'' factor. We propose an algorithm which adjusts the level of forgetting in a completely online fashion using the posterior predictive distribution. Our algorithm allows the model to accommodate various levels of change in the data-generating mechanism at different times. We apply our method to data from children with appendicitis who receive either a traditional (open) appendectomy or a laparoscopic procedure.