Research interests include: Bayesian inference of high-dimensional regression models, especially linear and generalized linear models. Together with Dr. Enes Makalic, he compiled an efficient toolbox to support the most advanced Bayesian contraction prior for high-dimensional regression models (available here); Information theory statistics, especially the application of information theory to statistical inference through the principle of minimum message/description length; Statistical genomics, risk prediction and mutation discovery, especially in the field of cancer genomics. He is interested in using mammography and machine learning techniques to improve risk prediction and stratification of women's future risk of breast cancer, to assist in creating personalized screening plans. Research area keywords Bayesian InferenceInformation TheoryMinimum Message LengthMinimum Description LengthStatistical and Data AnalysisShrinkage EstimationStatistical genomicsCancer genomicsMammography