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

Abstract Details

Activity Number: 193
Type: Contributed
Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
Sponsor: Social Statistics Section
Abstract - #308597
Title: Variable Selection for Propensity Score Models in Multilevel Data
Author(s): Bing Yu*+ and Guanglei Hong
Companies: University of Toronto and The University of Chicago
Address: 30 Charles St. West, 1407, Toronto, ON, M4Y 1R5, Canada
Keywords: bias ; causal inference ; confidence interval ; MSE ; prognostic score ; variance
Abstract:

Extant research on variable selection for propensity score models focus on single-level data. We intend to identify the optimal variable selection procedure for multilevel data with individuals nested within clusters. Using simulation data, this study evaluates the relative effectiveness of three alternative procedures: (a) adjusting for propensity score as a function of treatment predictors, (b) adjusting for propensity score as a function of outcome predictors, and (c) combining propensity score with prognostic score adjustment. We consider two scenarios: (1) individual-level treatment and outcome, and (2) cluster-level treatment and individual-level outcome. We also compare between random-intercept models and fixed-effect models for propensity score and prognostic score estimation. Evaluation criteria include bias, MSE, and confidence interval coverage percentage.


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.