|
|
|
This is the preliminary program for the 2009 Joint Statistical
Meetings in Washington, DC.
|
|
|
The views expressed here are those of the individual authors and not necessarily those of the ASA or its board, officers, or staff. Back to main JSM 2009 Program page |
= Applied Session,
= Theme Session,
= Presenter| CE_01C | Sat, 8/1/09, 8:30 AM - 5:00 PM | CC-204 A & B |
| Analysis of Multivariate Survival Data - Continuing Education - Course | ||
|
ASA |
||
| Instructor(s): Philip Hougaard, H. Lundbeck A/S | ||
| Multivariate survival data cover survival data, where the times are not independent. For example, (1) times of several related individuals (e.g., twins, siblings, married couples); (2) several times for the same individual, such as life history data (e.g., time to occurrence of disease, time to complication, time to death); (3) times to multiple occurrences of the same event (recurrent events). We will consider a study aim of both finding the effect of covariates and evaluating the degree of dependence. The course starts with a brief introduction to survival data. Frailty models for univariate data are described showing the mathematics behind mixture evaluations. The univariate data frailty model can model heterogeneity and extend standard models (e.g., proportional hazards to nonproportional hazards). Multivariate data examples are described and classified in six types. Probability mechanisms for dependence and correlation-like measures of dependence are described. Multistate models will be introduced, and it will be demonstrated how they can be set up and analyzed, both in the Markov case and in the general (non-Markov) case. The shared frailty model for multivariate data is the central model, allowing both covariate effects and dependence. The course emphasizes choice of model, advantages and disadvantages of each model, interpretation, and applications. The course covers parametric and nonparametric models and proportional hazards models and accelerated failure time models. Finally, extensions of the model are described briefly so to discuss shortcomings of assuming shared frailty. Software examples using (mostly) R are shown. | ||
|
JSM 2009
For information, contact jsm@amstat.org
or phone (888) 231-3473. If you have questions about the Continuing Education program,
please contact the Education Department. |