FHDI: An R package for fractional hot deck imputation

Jongho Im, In Ho Cho, Jae Kwang Kim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Fractional hot deck imputation (FHDI), proposed by Kalton and Kish (1984) and investigated by Kim and Fuller (2004), is a tool for handling item nonresponse in survey sampling. In FHDI, each missing item is filled with multiple observed values yielding a single completed data set for subsequent analyses. An R package FHDI is developed to perform FHDI and also the fully efficient fractional imputation (FEFI) method of (Fuller and Kim, 2005) to impute multivariate missing data with arbitrary missing patterns. FHDI substitutes missing items with a few observed values jointly obtained from a set of donors whereas the FEFI uses all the possible donors. This paper introduces FHDI as a tool for implementing the multivariate version of fractional hot deck imputation discussed in Im et al. (2015) as well as FEFI. For variance estimation of FHDI and FEFI, the Jackknife method is implemented, and replicated weights are provided as a part of the output.

Original languageEnglish
Pages (from-to)140-154
Number of pages15
JournalR Journal
Volume10
Issue number1
Publication statusPublished - 2018 Jul 1

Fingerprint

Imputation
Fractional
Sampling
Item Nonresponse
Survey Sampling
Jackknife
Variance Estimation
Multivariate Data
Substitute
Missing Data

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty

Cite this

Im, J., Cho, I. H., & Kim, J. K. (2018). FHDI: An R package for fractional hot deck imputation. R Journal, 10(1), 140-154.
Im, Jongho ; Cho, In Ho ; Kim, Jae Kwang. / FHDI : An R package for fractional hot deck imputation. In: R Journal. 2018 ; Vol. 10, No. 1. pp. 140-154.
@article{21399c0692e8459390b4f7ff393d9423,
title = "FHDI: An R package for fractional hot deck imputation",
abstract = "Fractional hot deck imputation (FHDI), proposed by Kalton and Kish (1984) and investigated by Kim and Fuller (2004), is a tool for handling item nonresponse in survey sampling. In FHDI, each missing item is filled with multiple observed values yielding a single completed data set for subsequent analyses. An R package FHDI is developed to perform FHDI and also the fully efficient fractional imputation (FEFI) method of (Fuller and Kim, 2005) to impute multivariate missing data with arbitrary missing patterns. FHDI substitutes missing items with a few observed values jointly obtained from a set of donors whereas the FEFI uses all the possible donors. This paper introduces FHDI as a tool for implementing the multivariate version of fractional hot deck imputation discussed in Im et al. (2015) as well as FEFI. For variance estimation of FHDI and FEFI, the Jackknife method is implemented, and replicated weights are provided as a part of the output.",
author = "Jongho Im and Cho, {In Ho} and Kim, {Jae Kwang}",
year = "2018",
month = "7",
day = "1",
language = "English",
volume = "10",
pages = "140--154",
journal = "R Journal",
issn = "2073-4859",
publisher = "R Foundation for Statistical Computing",
number = "1",

}

Im, J, Cho, IH & Kim, JK 2018, 'FHDI: An R package for fractional hot deck imputation', R Journal, vol. 10, no. 1, pp. 140-154.

FHDI : An R package for fractional hot deck imputation. / Im, Jongho; Cho, In Ho; Kim, Jae Kwang.

In: R Journal, Vol. 10, No. 1, 01.07.2018, p. 140-154.

Research output: Contribution to journalArticle

TY - JOUR

T1 - FHDI

T2 - An R package for fractional hot deck imputation

AU - Im, Jongho

AU - Cho, In Ho

AU - Kim, Jae Kwang

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Fractional hot deck imputation (FHDI), proposed by Kalton and Kish (1984) and investigated by Kim and Fuller (2004), is a tool for handling item nonresponse in survey sampling. In FHDI, each missing item is filled with multiple observed values yielding a single completed data set for subsequent analyses. An R package FHDI is developed to perform FHDI and also the fully efficient fractional imputation (FEFI) method of (Fuller and Kim, 2005) to impute multivariate missing data with arbitrary missing patterns. FHDI substitutes missing items with a few observed values jointly obtained from a set of donors whereas the FEFI uses all the possible donors. This paper introduces FHDI as a tool for implementing the multivariate version of fractional hot deck imputation discussed in Im et al. (2015) as well as FEFI. For variance estimation of FHDI and FEFI, the Jackknife method is implemented, and replicated weights are provided as a part of the output.

AB - Fractional hot deck imputation (FHDI), proposed by Kalton and Kish (1984) and investigated by Kim and Fuller (2004), is a tool for handling item nonresponse in survey sampling. In FHDI, each missing item is filled with multiple observed values yielding a single completed data set for subsequent analyses. An R package FHDI is developed to perform FHDI and also the fully efficient fractional imputation (FEFI) method of (Fuller and Kim, 2005) to impute multivariate missing data with arbitrary missing patterns. FHDI substitutes missing items with a few observed values jointly obtained from a set of donors whereas the FEFI uses all the possible donors. This paper introduces FHDI as a tool for implementing the multivariate version of fractional hot deck imputation discussed in Im et al. (2015) as well as FEFI. For variance estimation of FHDI and FEFI, the Jackknife method is implemented, and replicated weights are provided as a part of the output.

UR - http://www.scopus.com/inward/record.url?scp=85053908535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053908535&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85053908535

VL - 10

SP - 140

EP - 154

JO - R Journal

JF - R Journal

SN - 2073-4859

IS - 1

ER -

Im J, Cho IH, Kim JK. FHDI: An R package for fractional hot deck imputation. R Journal. 2018 Jul 1;10(1):140-154.