A comparison of two methods of estimating propensity scores after multiple imputation
A comparison of two methods of estimating propensity scores after multiple imputation
In many observational studies, analysts estimate treatment effects using propensity scores, e.g. by matching or sub-classifying on the scores. When some values of the covariates are missing, analysts can use multiple imputation to fill in the missing data, estimate propensity scores based on the m completed datasets, and use the propensity scores to estimate treatment effects. We compare two approaches to implement this process. In the first, the analyst estimates the treatment effect using propensity score matching within each completed data set, and averages the m treatment effect estimates. In the second approach, the analyst averages the m propensity scores for each record across the completed datasets, and performs propensity score matching with these averaged scores to estimate the treatment effect. We compare properties of both methods via simulation studies using artificial and real data. The simulations suggest that the second method has greater potential to produce substantial bias reductions than the first, particularly when the missing values are predictive of treatment assignment.
1-17
Mitra, R.
2b944cd7-5be8-4dd1-ab44-f8ada9a33405
Reiter, J.P.
fe1d67d4-02a9-4698-b36a-8efe8e83f0a3
Mitra, R.
2b944cd7-5be8-4dd1-ab44-f8ada9a33405
Reiter, J.P.
fe1d67d4-02a9-4698-b36a-8efe8e83f0a3
Mitra, R. and Reiter, J.P.
(2012)
A comparison of two methods of estimating propensity scores after multiple imputation.
Statistical Methods in Medical Research, .
(doi:10.1177/0962280212445945).
Abstract
In many observational studies, analysts estimate treatment effects using propensity scores, e.g. by matching or sub-classifying on the scores. When some values of the covariates are missing, analysts can use multiple imputation to fill in the missing data, estimate propensity scores based on the m completed datasets, and use the propensity scores to estimate treatment effects. We compare two approaches to implement this process. In the first, the analyst estimates the treatment effect using propensity score matching within each completed data set, and averages the m treatment effect estimates. In the second approach, the analyst averages the m propensity scores for each record across the completed datasets, and performs propensity score matching with these averaged scores to estimate the treatment effect. We compare properties of both methods via simulation studies using artificial and real data. The simulations suggest that the second method has greater potential to produce substantial bias reductions than the first, particularly when the missing values are predictive of treatment assignment.
Text
mitrareiter_smimrmaintext.pdf
- Other
Text
mitrareiter_smimronlinesupplement.pdf
- Other
Text
180701MITRA10.pdf
- Version of Record
Restricted to Repository staff only
Request a copy
More information
e-pub ahead of print date: 11 June 2012
Organisations:
Statistical Sciences Research Institute, Southampton Statistical Research Inst.
Identifiers
Local EPrints ID: 180701
URI: http://eprints.soton.ac.uk/id/eprint/180701
ISSN: 0962-2802
PURE UUID: 3948e9a7-2230-4669-82e6-a22892796b59
Catalogue record
Date deposited: 12 Apr 2011 14:40
Last modified: 14 Mar 2024 02:53
Export record
Altmetrics
Contributors
Author:
J.P. Reiter
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