Statistical Methods for Risk Prediction and Precision Medicine

Catalog description

This is an advanced elective course for graduate students in Biostatistics, Statistics, Epidemiology, and other BGS disciplines. It will cover various topics for evaluating the performance of biomarkers to predict risk of clinical or disease outcomes, specifically including relative, absolute and competing risks for binary and time-to-disease outcomes; statistical inference for quantifying predictive accuracy with binary and time-to-event outcomes; statistical methods and inference for case-control study designs; Efficient study design issues for biomarker evaluation. This course is designed to help students 1) understand various concepts of risk in the medical literature; 2) understand various statistical methods for evaluating prediction performance of biomarkers and diagnostic tests and for designing efficient biomarker studies; 3) improve the ability to read critically papers published in statistical and medical journals on related topics; and 4) develop research ideas for risk prediction. Upon successfully completing this course, students will be able to: 1) Conduct statistical analysis for evaluating prediction performance of biomarkers and diagnostic tests; 2) Have a better ability to read and understand papers published in statistical and medical journals on related topics; and 3) Be well prepared to work on related topics for dissertation.