|
Activity Number:
|
9
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
IMS
|
| Abstract - #307923 |
|
Title:
|
Semiparametric Sequential Estimators for Dynamic Causal Models
|
|
Author(s):
|
Michael H. Lechner*+
|
|
Companies:
|
University of St. Gallen
|
|
Address:
|
Bodanstr. 8, SIAW, St. Gallen, 9000, Switzerland
|
|
Keywords:
|
Dynamic treatment effects ; causal effects ; nonparametric identification ; sequential randomisation ; programme evaluation ; panel data
|
|
Abstract:
|
This paper proposes inverse selection probability weighting and sequential propensity score matching to estimate dynamic causal effects. A Monte Carlo study shows that the suggested matching estimators perform well in small and medium sized samples. A re-evaluation of some parts of the Swiss active labor market policies based on a dynamic causal model allows the discussion of issues concerning the implementation of the new methods.
|
