Adaptive Experimental Design Using the Propensity Score

Jinyong Hahn (), Keisuke Hirano () and Dean Karlan ()
Additional contact information
Jinyong Hahn: Department of Economics, UCLA

Working Papers from Economic Growth Center, Yale University

Abstract: Many social experiments are run in multiple waves, or are replications of earlier social experiments. In principle, the sampling design can be modified in later stages or replications to allow for more efficient estimation of causal effects. We consider the design of a two-stage experiment for estimating an average treatment effect, when covariate information is available for experimental subjects. We use data from the first stage to choose a conditional treatment assignment rule for units in the second stage of the experiment. This amounts to choosing the propensity score, the conditional probability of treatment given covariates. We propose to select the propensity score to minimize the asymptotic variance bound for estimating the average treatment effect. Our procedure can be implemented simply using standard statistical software and has attractive large-sample properties.

Keywords: experimental design; propensity score; efficiency bound (search for similar items in EconPapers)
JEL-codes: C1 C14 C9 C93 C13 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-ecm and nep-exp
Date: 2009-01
View list of references

Downloads: (external link)
http://www.econ.yale.edu/growth_pdf/cdp969.pdf (application/pdf)

Related works:
Working Paper: Adaptive Experimental Design Using the Propensity Score (2009)
Working Paper: Adaptive Experimental Design Using the Propensity Score (2008)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:egc:wpaper:969

Access Statistics for this paper

More papers in Working Papers from Economic Growth Center, Yale University
Contact information at EDIRC.
Series data maintained by Louise Danishevsky ().