The University of Southampton
University of Southampton Institutional Repository

Estimation of treatment effects in observational studies by recovering the assignment probabilities and the population model

Estimation of treatment effects in observational studies by recovering the assignment probabilities and the population model
Estimation of treatment effects in observational studies by recovering the assignment probabilities and the population model
In observational studies the assignment of units to treatments is with unknown probabilities. Consequently, estimation and comparison of treatment effects based on the empirical distributions of the response under the various treatments can be biased since units exposed to one treatment could differ in important but unknown characteristics from units exposed to other treatments.

In this article we study the plausibility of analyzing observational data by deriving the parametric distribution of the observed response under a given treatment as a function of the distribution that would be obtained under a strongly ignorable assignment, and the assignment process, which is modeled as a function of the observed data (the response and covariate values). The use of this approach is founded by showing that the sample distribution of the observed responses is identifiable under some general conditions. The goodness of fit of this distribution can be tested by using standard test statistics since it refers to the observed data, but we also develop a new test. The proposed approach allows also testing the assumptions underlying the use of methods that employ instrumental variables, or methods that use propensity scores with a given set of covariates.

We assess the performance of the proposed approach and compare it to existing approaches using data collected in the year 2000 by OECD for the Programme for International Student Assessment (PISA). In the present application we compare students’ scores in mathematics between public and private schools in Ireland and conclude, somewhat surprisingly, that the public schools perform better than the private schools. This finding is supported by one of the existing methods as well.
M07/10
Southampton Statistical Sciences Research Institute, University of Southampton
Pfeffermann, Danny
c7fe07a0-9715-42ce-b90b-1d4f2c2c6ffc
Landsman, Victoria
836210b8-0254-4387-83e2-e6ec44615b9c
Pfeffermann, Danny
c7fe07a0-9715-42ce-b90b-1d4f2c2c6ffc
Landsman, Victoria
836210b8-0254-4387-83e2-e6ec44615b9c

Pfeffermann, Danny and Landsman, Victoria (2007) Estimation of treatment effects in observational studies by recovering the assignment probabilities and the population model (S3RI Methodology Working Papers, M07/10) Southampton, GB. Southampton Statistical Sciences Research Institute, University of Southampton 38pp.

Record type: Monograph (Working Paper)

Abstract

In observational studies the assignment of units to treatments is with unknown probabilities. Consequently, estimation and comparison of treatment effects based on the empirical distributions of the response under the various treatments can be biased since units exposed to one treatment could differ in important but unknown characteristics from units exposed to other treatments.

In this article we study the plausibility of analyzing observational data by deriving the parametric distribution of the observed response under a given treatment as a function of the distribution that would be obtained under a strongly ignorable assignment, and the assignment process, which is modeled as a function of the observed data (the response and covariate values). The use of this approach is founded by showing that the sample distribution of the observed responses is identifiable under some general conditions. The goodness of fit of this distribution can be tested by using standard test statistics since it refers to the observed data, but we also develop a new test. The proposed approach allows also testing the assumptions underlying the use of methods that employ instrumental variables, or methods that use propensity scores with a given set of covariates.

We assess the performance of the proposed approach and compare it to existing approaches using data collected in the year 2000 by OECD for the Programme for International Student Assessment (PISA). In the present application we compare students’ scores in mathematics between public and private schools in Ireland and conclude, somewhat surprisingly, that the public schools perform better than the private schools. This finding is supported by one of the existing methods as well.

Text
46012-01.pdf - Other
Download (477kB)

More information

Published date: 2007

Identifiers

Local EPrints ID: 46012
URI: http://eprints.soton.ac.uk/id/eprint/46012
PURE UUID: 06be9103-ecaa-4759-bcda-a46cc024c8dd

Catalogue record

Date deposited: 14 May 2007
Last modified: 15 Mar 2024 09:15

Export record

Contributors

Author: Victoria Landsman

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×