Campus Units

Statistics

Document Type

Article

Publication Version

Published Version

Publication Date

2014

Journal or Book Title

Survey Methodology

Volume

40

Issue

2

First Page

211

Last Page

230

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.

Comments

This article is published as Kim, Jae Kwang, and Shu Yang. "Fractional hot deck imputation for robust inference under item nonresponse in survey sampling." Survey Methodology 40, no. 2 (2014): 211-230. Posted with permission.

Rights

Source: Statistics Canada; Survey Methodology; December 2014. Reproduced and distributed on an "as is" basis with the permission of Statistics Canada.

Copyright Owner

Minister of Industry

Language

en

File Format

application/pdf

Share

COinS