Research and Teaching Interests

Dr. McLain has a broad range of statistical interests including Bayesian methods for high-dimensional linear regression, modeling complex longitudinal and clustered data, length-biased survival analysis, and multiple testing. Recently, most of his research has focused on computationally feasible Bayesian methods for prediction, predictive inference, and variable selection for high-dimensional regression models. His areas of application are in maternal child-health, nutrition, disease mapping (with various outcomes), and neuroimaging. He is currently an Associate Editor for Statistics in Medicine, The American Statistician, a member of the Statistical Review Board for the American Society of Nutrition, and is a Statistical Consultant for the American Journal of Obstetrics and Gynecology.