JSM 2015 Preliminary Program

Online Program Home
My Program

Abstract Details

Activity Number: 77
Type: Contributed
Date/Time: Sunday, August 9, 2015 : 4:00 PM to 5:50 PM
Sponsor: Survey Research Methods Section
Abstract #315596 View Presentation
Title: Applying Pattern-Mixture Models for Estimation from Multiple Data Sources
Author(s): Jeffrey Gonzalez* and John L. Eltinge
Companies: Bureau of Labor Statistics and Bureau of Labor Statistics
Keywords: Administrative data ; Big data ; Coverage error ; Data integration
Abstract:

Statistical organizations are increasingly exploring the integration of sample survey data with information provided by alternative data sources, e.g. commercial transaction data. One issue is that these data sources may not satisfy survey sample design requirements (e.g. probability sampling). Thus, the quality of the statistical products produced from the integrated data will depend on the mechanisms that link the data sources to the target population of interest. One technique that may be used to produce high quality survey products from integrated data sources is pattern-mixture models (Little and Rubin 1993). Pattern-mixture models have traditionally been used in surveys with nonignorable nonresponse. In those applications, response indicators define subpopulations of missing data patterns and inferences are made conditional on those patterns. Applying these models to data integration problems seems reasonable since subpopulations can be defined by indicators of the unit being captured or represented by one or more of the alternative data sources. As such, we explore the extent to which pattern mixture models can be used to integrate survey data with alternative data sources.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2015 program





For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

2015 JSM Online Program Home