|
Activity Number:
|
10
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
ENAR
|
| Abstract - #307947 |
|
Title:
|
Analysis of Longitudinal and Response/Failure Time Data from an Observational Study with Missing Observations
|
|
Author(s):
|
Dianne M. Finkelstein*+ and Natasa Rajicic and David A. Schoenfeld
|
|
Companies:
|
Harvard/MGH and Pfizer Inc. and MGH/Harvard
|
|
Address:
|
50 Staniford Street, Boston, MA, 02114,
|
|
Keywords:
|
interval censored ; failure time ; multi-state
|
|
Abstract:
|
Observational studies often are interested in the relationship between a longitudinal marker and clinical improvement (e.g., response) or progression. Often both the marker and the determination of clinical status are assessed at regular clinic visits. If a subject misses a visit, the response and/or progression time will only be known to have occurred in the interval bounded by the last negative, and first positive visit times (interval censored event time data). In addition, the marker data will be missing. This talk will focus on methods for analysis of data from such a study. The methods are discussed in the context of data from a diabetes and a trauma study.
|
