Open Access
June 2011 Variance estimation for nearest neighbor imputation for US Census long form data
Jae Kwang Kim, Wayne A. Fuller, William R. Bell
Ann. Appl. Stat. 5(2A): 824-842 (June 2011). DOI: 10.1214/10-AOAS419


Variance estimation for estimators of state, county, and school district quantities derived from the Census 2000 long form are discussed. The variance estimator must account for (1) uncertainty due to imputation, and (2) raking to census population controls. An imputation procedure that imputes more than one value for each missing item using donors that are neighbors is described and the procedure using two nearest neighbors is applied to the Census long form. The Kim and Fuller [Biometrika 91 (2004) 559–578] method for variance estimation under fractional hot deck imputation is adapted for application to the long form data. Numerical results from the 2000 long form data are presented.


Download Citation

Jae Kwang Kim. Wayne A. Fuller. William R. Bell. "Variance estimation for nearest neighbor imputation for US Census long form data." Ann. Appl. Stat. 5 (2A) 824 - 842, June 2011.


Published: June 2011
First available in Project Euclid: 13 July 2011

zbMATH: 05961693
MathSciNet: MR2840177
Digital Object Identifier: 10.1214/10-AOAS419

Keywords: fractional imputation , hot deck imputation , nonresponse , replication variance estimation

Rights: Copyright © 2011 Institute of Mathematical Statistics

Vol.5 • No. 2A • June 2011
Back to Top