|
Activity Number:
|
13
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #307530 |
|
Title:
|
Real-Time Learning for Heterogeneous Multivariate Longitudinal Data
|
|
Author(s):
|
W. John Boscardin*+ and Hector Lemus
|
|
Companies:
|
University of California, Los Angeles and University of California, Los Angeles
|
|
Address:
|
Department of Biostatistics, Los Angeles, CA, 90095,
|
|
Keywords:
|
state space models ; Bayesian forecasting ; smoothing splines
|
|
Abstract:
|
Medical research often involves the longitudinal collection of multivariate measurements on extremely heterogeneous subjects with the goals of estimating the overall and subject-specific time courses of one or more of the measurements, assessing the correlation of pairs of the measurements, and generating short- and long-term predictions for subjects throughout the data collection period. A Bayesian multivariate smoothing spline model in a state-space framework can be used to analyze these data in a prospective real-time setting (i.e., it is possible to efficiently learn about the current subject's recent time course, correlations, and predictions given the available data for the current subject and the ensemble of previous subjects). We demonstrate this methodology using data from severe head trauma subjects.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2006 program |
