Colloquium - 8 Oct 1998

Department of Statistics
Texas A&M University

STATISTICS COLLOQUIUM

DEPARTMENT OF STATISTICS
Texas A&M University

Elizabeth Slate

Cornell University

Statistical Models for Longitudinal Biomarkers of Disease

ABSTRACT: This talk concerns the analysis of serial biomarkers to screen and monitor individuals in a given population for onset of a disease of interest. The application used throughout is the analysis of longitudinal prostate-specific antigen (PSA) measurements as a biomarker for prostate cancer. Linear and nonlinear mixed-effects models are used to study the growth of PSA levels for those subsequently diagnosed with prostate cancer and those not. The focus, however, is the use of a Bayesian hierarchical model to estimate changepoints in the PSA trajectories that represent cancer onset. The changepoints may be estimated retrospectively or prospectively. Receiver operating characteristic (ROC) curves are used to compare several diagnostic rules, including a rule based on the posterior distribution of the changepoints.

DATE:	Thursday, October 8, 1998
TIME:	4:00 p.m.-5:00 p.m.
PLACE:	Room 150, Blocker

Refreshments will be served in the Blocker Building, Room 447, at 3:30 p.m.

Copyright © Unless otherwise stated, all contents of these web pages are copyright by their respective authors or by the Department of Statistics, Texas A&M University, 1995-1998. Comments and questions about this site should be sent to web@stat.tamu.edu.