The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
Activity Number:
|
440
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, August 1, 2012 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Survey Research Methods
|
Abstract - #303631 |
Title:
|
Data Fusion via Multiple Imputation
|
Author(s):
|
Jerome P Reiter*+
|
Companies:
|
Duke University
|
Address:
|
Box 90251, Durham, NC, , USA
|
Keywords:
|
matching ;
missing ;
Bayesian ;
imputation ;
fusion
|
Abstract:
|
Often analysts seek to combine information from two (or more) different sources, i.e., data fusion. I discuss a framework for multiple imputation inferences for data fusion contexts in which two sources do not have any overlapping records. The basic idea is to (i) formulate a joint model for the concatenated data, (ii) posit values of any unobservable parameters in the model, and (iii) generate multiple imputations under the posited model. However, in this context, the usual multiple imputation combining rules of Rubin (1987) lead to biased estimates of variance, even when the posited parameter values are correct. I present an alternative framework that enables valid estimation of variances for these data fusion settings.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2012 program
|
2012 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.