|
Activity Number:
|
430
|
|
Type:
|
Luncheons
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 12:30 PM to 1:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #307514 |
|
Title:
|
Interval Censored Time-to-Event Data: Examples, Analyses, and Assumptions
|
|
Author(s):
|
Daohai Yu*+
|
|
Companies:
|
Duke University
|
|
Address:
|
406 Somersview Drive, Chapel Hill, NC, 27514,
|
|
Keywords:
|
interval censoring ; conditional model ; dependent censoring ; discretionary visits ; serial screening ; survival analysis
|
|
Abstract:
|
The random censorship assumption is violated often in interval censored (IC) time-to-event data, such as when the data arise from a serial screening and the timing of screening potentially could depend on the patient's health status. Some examples of dependent IC event data will be discussed, along with data analysis methods currently available for IC time-to-event data. Underlying assumptions for each method will be examined and compared. In particular, a new likelihood-based approach coupled with a class of innovative conditional models for dependent, interval-censored, time-to-event data with a marker for discretionary visits will be discussed and compared with the current analysis methods assuming independent censoring.
|
- 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 |
