|
Activity Number:
|
199
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #307268 |
|
Title:
|
Quantile Regression Methods for Modeling CD4 T-Cell Trajectory among HIV-Infected Men and Women on Long Term, Highly Active Antiretroviral Therapy
|
|
Author(s):
|
Haitao Chu*+ and Ying Wei and Alvaro Munoz and Stephen J. Gange
|
|
Companies:
|
Johns Hopkins Bloomberg School of Public Health and Columbia University and Johns Hopkins Bloomberg School of Public Health and Johns Hopkins Bloomberg School of Public Health
|
|
Address:
|
N 615 Wolfe Street, Baltimore, MD, 21205,
|
|
Keywords:
|
conditional quantile regression methods ; longitudinal data analysis ; multicenter aids cohort study ; Women's Interagency HIV Study ; CD4 cell count
|
|
Abstract:
|
Estimating CD4 cell count trajectories for HIV-infected subjects has traditionally relied on linear/nonlinear random effect models or generalized estimating equation approaches. The construction of predictive reference curves for an individual, which has important clinical significance, has often relied on normal theory. In the analysis of longitudinal data with unequally spaced measurements, non-parametric conditional quantile regression methods (QR) offer a complementary strategy for estimating conditional quantile functions based on prior history and other covariates. The authors provided a case study using QR to estimate CD4 cell count trajectories over a 7-year period following HAART initiation for 404 HIV-infected men in the Multicenter AIDS Cohort Study and 609 HIV-infected women in the Women's Interagency HIV Study. The advantages of QR are illustrated.
|
