|
Activity Number:
|
19
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #309525 |
|
Title:
|
Institutionalization at Follow-Up: An Application of Principal Stratification to the Evaluation of Substance Abuse Treatment
|
|
Author(s):
|
Daniel McCaffrey*+ and Beth Ann Griffin
|
|
Companies:
|
RAND Corporation and RAND Corporation
|
|
Address:
|
4570 Fifth Avenue Suite 600, Pittsburgh, PA, 15213-2665,
|
|
Keywords:
|
potential outcomes ; treatment effects
|
|
Abstract:
|
Participants in longitudinal studies on the effects drug treatment and criminal justice system interventions are at high risk for institutionalization (i.e., spending time in an environment where their freedom to use drugs, commit crimes, or engage in risky behavior may be circumscribed). Methods used for estimating treatment effects in the presence of institutionalization during the follow-up can be highly sensitive to assumptions that are unlikely to be met in applications. In this paper, we extend the methods of principal stratification to model institutionalization at follow-up for the estimation of the effect of residential substance abuse treatment versus outpatient services. We discuss practical issues in applying the model to data and show via simulation that the model can recover true effects, but that careful selection of starting values is essential for consistent estimation.
|
