|
Activity Number:
|
130
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 7, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
General Methodology
|
| Abstract - #304924 |
|
Title:
|
Estimation of Treatment Effects in Observational Studies
|
|
Author(s):
|
Danny Pfeffermann*+
|
|
Companies:
|
Hebrew University/University of Southampton
|
|
Address:
|
Department of Statistics, Hebrew University, Jerusalem, 91905, Israel
|
|
Keywords:
|
randomized experiment ; propensity scores ; instrumental variables ; sample distribution ; sample surveys ; PISA
|
|
Abstract:
|
In observational studies the assignment of units to treatments is with unknown probabilities, and the units exposed to the various treatments could differ in important unknown characteristics. Consequently, estimation and comparison of treatment effects based on the empirical outcome distributions can be misleading. We consider an approach to deal with this problem that attempts to approximate the parametric distribution of the observed responses under a given treatment as a function of the distribution that would be obtained under strongly ignorable assignments and the assignment rule, which is modeled as a function of the observed responses and covariates. The use of this approach is founded by showing that the distribution of the observed responses is identifiable under fairly general conditions. The goodness of fit of this distribution can be tested using simple test statistics
|
- 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 2006 program |
