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:
|
626
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 2, 2012 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Survey Research Methods
|
Abstract - #306189 |
Title:
|
Using Administrative Records to Augment Unit Nonresponse to Facilitate Hot-Deck Imputation
|
Author(s):
|
Vincent Welch*+ and Fang Wang
|
Companies:
|
NORC and NORC
|
Address:
|
1708 Dempster St., Evanston, IL, 60202, United States
|
Keywords:
|
Imputation ;
Hot-deck ;
Administrative records ;
Unit nonresponse
|
Abstract:
|
When weighting is not an attractive option for treating unit-level nonresponse (UNR), as in a census, the use of administrative data and imputation can improve the quality of a data set. The Survey of Earned Doctorates (SED) is a census of all new research doctorate recipients in the U.S. The SED boasts a 92.3% unit-level response rate. The item response rates are generally well above 90 percent. UNR is augmented with administrative data from the doctorate-granting institution, which brings many key variables to 100% item response. The NSF commissioned an investigation to determine if imputation would be feasible in the SED. We used modeling to determine the strongest relationships among the variables, and serpentine sorting to organize a nearest neighbor hot-deck imputation procedure. We tested the univariate distributions of the pre-and post-imputation data sets and the relationships among the pre- and post-imputation variables. The relationships among the post-imputation data set were not significantly different from the pre-imputation data set. Overall, imputation showed promise in treating UNR when administrative data are used to augment self-reported data.
|
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.