Fractional hot deck imputation for robust inference under item nonresponse in survey sampling

View the most recent version.

Archived Content

Information identified as archived is provided for reference, research or recordkeeping purposes. It is not subject to the Government of Canada Web Standards and has not been altered or updated since it was archived. Please "contact us" to request a format other than those available.

Archived

This page has been archived on the Web.

Jae Kwang Kim and Shu Yang^Note 1

• [PDF]

Abstract

Parametric fractional imputation (PFI), proposed by Kim (2011), is a tool for general purpose parameter estimation under missing data. We propose a fractional hot deck imputation (FHDI) which is more robust than PFI or multiple imputation. In the proposed method, the imputed values are chosen from the set of respondents and assigned proper fractional weights. The weights are then adjusted to meet certain calibration conditions, which makes the resulting FHDI estimator efficient. Two simulation studies are presented to compare the proposed method with existing methods.

Key Words: EM algorithm; Kullback-Leibler information; Missing at random (MAR); Multiple imputation.

Table of content

• 1. Introduction
• 2. Basic setup
• 3. Proposed method
• 4. Robustness
• 5. Simulation study
• 6. Concluding remarks
• Acknowledgements
• Appendix
• References

Notes