Hi Valerio,
Here is one piece which uses the predictive Bayesian approach to statistical inference for causal quantities ( see also http://andrewgelman.com/2009/07/10/rubinism_separa/ ) with missing outcomes:
@article{barnard2003psa,
Author = {Barnard, J. and Frangakis, C.E. and Hill, J.L. and Rubin, D.B.},
Journal = {Journal of the American Statistical Association},
Number = {462},
Pages = {299--324},
Title = {{Principal Stratification Approach to Broken Randomized Experiments: A Case Study of School Choice Vouchers in New York City.}},
Volume = {98},
Year = {2003}}
This approach does not separate multiple imputation per se from estimation, but could be used in place of multiple imputation+matching.
Best,
Jake
Jake Bowers
Associate Professor
Political Science and Statistics and NCSA
University of Illinois @ Urbana-Champaign
http://jakebowers.org
[log in to unmask]
On Jul 8, 2014, at 11:48 AM, Valerio Bacak <[log in to unmask]> wrote:
> Hi all,
>
> I haven't had much luck finding (convincing) references on matching with
> multiply imputed data. Any pointers would be highly appreciated. I'd be
> happy to share the references I receive with the list.
>
> Thanks,
> Valerio
>
> --
> Valerio Bacak
> PhD Candidate
> Department of Sociology
> University of Pennsylvania
> https://sites.sas.upenn.edu/vbacak
>
>
>
>
>
> **********************************************************
> Political Methodology E-Mail List
> Editors: Ethan Porter <[log in to unmask]>
> Gregory Whitfield <[log in to unmask]>
> **********************************************************
> Send messages to [log in to unmask]
> To join the list, cancel your subscription, or modify
> your subscription settings visit:
>
> http://polmeth.wustl.edu/polmeth.php
>
> **********************************************************
|