This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 156
Type: Topic Contributed
Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
Sponsor: Health Policy Statistics Section
Abstract - #308173
Title: Unmeasured Covariates in Repeated Observational Studies
Author(s): Bo Lu*+ and Chih-Lin Li
Companies: The Ohio State University and The Ohio State University
Address: B110 Starling-Loving Hall, Columbus, OH, 43210, U.S.
Keywords: Propensity score matching ; Potential outcome ; sensitivity analysis ; time-dependent effect modifier ; suboptimal matching
Abstract:

In health service research, many intervention programs are observational studies and successful programs may be repeated over time. How to evaluate the program effect is challenging because the effect might not be stable over time or possible health policy changes interact with the program. Using potential outcome framework, we identify causal parameters for various effects. Propensity score matching based estimators are proposed to remove selection bias due to observed covariates. The impact due to unmeasured covariates may come from two sources: time-dependent effect modifiers or confounders associated with both treatment selection and outcome. We propose a multi-time-point matching estimator and a sensitivity analysis to address those two issues separately. The methodology is illustrated with an Italian smoking cessation program which enrolled participants every year since 2001.


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 2010 program




2010 JSM Online Program Home

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.