Advances in molecular technology have shifted the development of new drugs towards precision medicine, to identify right patients for the right treatment. The success of precision medicine lies in development of biomarker-based subgroup selection strategy to match the disease with specific therapies for individual patients. This presentation covers three steps to develop a subgroup selection strategy: 1) biomarker identification, 2) subgroup selection, and 3) subgroup analysis to assess clinical utility. Biomarker identification involves fitting interaction models to identify sets of potential prognostic and/or predictive biomarkers from a set of measured genomic variables. Subgroup Selection develops a prediction model based on the biomarkers identified to partition patients into subgroups that are homogeneous with respect to disease outcomes and/or responses to a specific treatment. Subgroup Analysis evaluates accuracy of patient treatment assignment and assesses enhancement of treatment efficacy. Procedures are illustrated by simulations and analyses of cancer datasets. Major statistical issues and challenges will be discussed, including identification of prognostic and predictive biomarkers, false and true positives in biomarker identification respect to predictive model development, safety biomarkers for drug-induced toxicity, subgroup domain and clinical target variable.