STOR Colloquium: Xinyi Xu (The Ohio State University)

Calibrated Bayes factors for model comparison

Bayes factor is a widely used tool for Bayesian hypothesis testing and model comparison.  However, its value can be greatly affected by the prior elicitation for the model parameters.  When the prior information is weak, people often use proper priors with large variances.  In this work, we show that when the models under comparisons differ in dimensions, Bayes factors under convenient diffuse priors can be very misleading.  Therefore, we propose an innovative method called calibrated Bayes factor, which uses data to calibrate the prior distributions before computing Bayes factors.  We show that this method provides reliable and robust model preferences under various true models.  It is applicable to a large variety of model comparison problems because it makes no assumption on model forms (parametric or nonparametric) and can be used for both proper and improper priors.

Refreshments will be served at 3:30pm in the 3rd floor lobby of Hanes Hall