Abstract Details
Activity Number:
|
299
|
Type:
|
Topic Contributed
|
Date/Time:
|
Tuesday, August 11, 2015 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract #315059
|
View Presentation
|
Title:
|
Weighted Estimating Equations Based on Response Propensities in Terms of Covariates That Are Observed Only for Responders
|
Author(s):
|
Eric Slud*
|
Companies:
|
U.S. Census Bureau
|
Keywords:
|
Survey weights ;
Missing at Random ;
Calibration ;
Consistency ;
Efficiency
|
Abstract:
|
Weighted estimating equations are frequently used to estimate parameters in surveys and randomized experiments in settings where there is missing data due to nonresponse. The weights are generally related to the reciprocals of the "propensities" or conditional probabilities of response for individual subjects in terms of subject-level covariates which are known or observed even for nonresponding subjects. The consistency properties for the resulting estimating equations depend crucially on the "Missing at Random" (MAR) property for outcome variables in terms of the covariates used to construct the weights. Yet the MAR property may hold only when propensities reflect covariates observable simultaneously with outcome-variable responses. This talk describes settings in which such propensities may be used to adjust for nonresponse, consistently and sometimes efficiently, when population-level information about the full set of covariates is known or estimated from external data sources. The methods will be illustrated using data from the American Community Survey.
|
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
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.