Abstract Details
Activity Number:
|
671
|
Type:
|
Topic Contributed
|
Date/Time:
|
Thursday, August 8, 2013 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract - #309706 |
Title:
|
Some Thoughts on Calibration Applications for Multipurpose Estimations
|
Author(s):
|
Yan Liu*+ and Yuqi Liu
|
Companies:
|
Statistics of Income/IRS and The George Washington University
|
Keywords:
|
Auxiliary variable ;
Composite calibration estimation ;
Generalized linear regression ;
Multipurpose estimation ;
Sample weight ;
Weight calibration
|
Abstract:
|
The linear calibration approach is commonly used to adjust sample weights for multipurpose estimations. Although the linear calibration estimator has many good properties, it has two major limitations. One is the efficiency issue and the other is the convergence issue. Many modified methods have been suggested in the literature, but they do not address both issues at the same time. The modified methods intended for efficiency gain only apply to a single study variable, while modified methods intended for stable estimations for multiple study variables do not offer efficiency gains. In this paper, we first review some modified calibration methods and offer some thoughts about calibration applications to balance efficiency gain and multipurpose use. In particular, we propose a composite calibration weighting method and some modifications of the regular linear calibration method. The proposed methods aim at improving the efficiency for some 'priority' study variables, while still keeping the multipurpose property. Results of a limited simulation study are presented as well.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2013 program
|
2013 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.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.