Department of Statistics, The Ohio State University
Statistics and Biostatistics Colloquium Series

We propose an empirical Bayes method for variable selection and coefficient estimation in linear regression models. The method is based on a particular hierarchical Bayes formulation, and the estimator is shown to be closely related to the LASSO estimator. Such a connection allows us to take advantage of the recently developed quick LASSO algorithm to compute the empirical Bayes estimate, and provides new ways to select the tuning parameter in the LASSO method. Unlike previous empirical Bayes variable selection methods, which in most practical situation can only be implemented through a greedy stepwise algorithm, our method gives a global solution efficiently. Simulations show that the proposed method compares favorably with other variable selection and estimation methods in terms of variable selection, estimation accuracy, and computation speed. This is a joint work with Professor Yi Lin.