|
Activity Number:
|
18
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 11, 2002 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
General Methodology
|
| Abstract - #301127 |
|
Title:
|
Identifying Risk Factors Under Informative Loss to Follow-up
|
|
Author(s):
|
Christiana Drake*+ and Richard Levine
|
|
Affiliation(s):
|
University of California, Davis and University of California, Davis
|
|
Address:
|
One Shields Avenue, Davis, California, 95616, USA
|
|
Keywords:
|
longitudinal studies ; informative loss ; predictors of outcome ; mental health
|
|
Abstract:
|
Prospective cohort studies are used to identify causes of disease. These studies enroll subjects and follow them for a certain time period. Onset of disease may be recorded continuously or at fixed time intervals. Follow-up studies typically experience varying degrees of loss to follow-up. Subjects are lost due to competing risks, unwillingness to continue with the study, and other reasons. Loss to follow-up is usually assumed to be non-informative. In studies of predictors of recovery from mental illness, however, subjects recovering are more likely to drop out of the study, and censoring is informative. We will develop some rules which allow us to assess the probability of recovery, given a factor recorded at baseline, for the whole cohort based on what is observed in the non-censored population. Loss to follow-up is assumed to be positively associated with recovery from disease.
|
- 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 2002 program |
