Preserving logical relations while estimating missing values

A.G. de Waal, Wieger Coutinho

Research output: Contribution to journalArticleScientificpeer-review

13 Downloads (Pure)

Abstract

Item-nonresponse is often treated by means of an imputation technique. In some cases, the data have to satisfy certain constraints, which are frequently referred to as edits. An example of an edit for numerical data is that the profit of an enterprise equals its turnover minus its costs. Edits place restrictions on the imputations that are allowed and hence complicate the imputation process. In this paper we explore an adjustment approach. This adjustment approach consists of three steps. In the first step, the imputation step, nearest neighbour hot deck imputation is used to find several pre-imputed values. In a second step, the adjustment step, these pre-imputed values are adjusted so the resulting records satisfy all edits. In a third step, the best donor record is selected. The adjusted record corresponding to that donor record is the final imputed record. In principle, a potential donor that is not the closest to the record to be imputed may still give the best results after adjustment. In this paper we therefore focus on the number of potential donor records that are considered in the imputation step.
Keywords: Nearest-neighbour Imputation, Edit restrictions, Linear programming, Data adjustment
Original languageEnglish
Pages (from-to)47-59
JournalRomanian Statistical Review
Volume2017
Issue number3
Publication statusPublished - 2017

Cite this

@article{c139f0c7f5d44a22a47860159f38b39e,
title = "Preserving logical relations while estimating missing values",
abstract = "Item-nonresponse is often treated by means of an imputation technique. In some cases, the data have to satisfy certain constraints, which are frequently referred to as edits. An example of an edit for numerical data is that the profit of an enterprise equals its turnover minus its costs. Edits place restrictions on the imputations that are allowed and hence complicate the imputation process. In this paper we explore an adjustment approach. This adjustment approach consists of three steps. In the first step, the imputation step, nearest neighbour hot deck imputation is used to find several pre-imputed values. In a second step, the adjustment step, these pre-imputed values are adjusted so the resulting records satisfy all edits. In a third step, the best donor record is selected. The adjusted record corresponding to that donor record is the final imputed record. In principle, a potential donor that is not the closest to the record to be imputed may still give the best results after adjustment. In this paper we therefore focus on the number of potential donor records that are considered in the imputation step.Keywords: Nearest-neighbour Imputation, Edit restrictions, Linear programming, Data adjustment",
author = "{de Waal}, A.G. and Wieger Coutinho",
year = "2017",
language = "English",
volume = "2017",
pages = "47--59",
journal = "Romanian Statistical Review",
issn = "1018-046X",
publisher = "Romanian National Institute of Statistics",
number = "3",

}

Preserving logical relations while estimating missing values. / de Waal, A.G.; Coutinho, Wieger.

In: Romanian Statistical Review , Vol. 2017, No. 3, 2017, p. 47-59.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Preserving logical relations while estimating missing values

AU - de Waal, A.G.

AU - Coutinho, Wieger

PY - 2017

Y1 - 2017

N2 - Item-nonresponse is often treated by means of an imputation technique. In some cases, the data have to satisfy certain constraints, which are frequently referred to as edits. An example of an edit for numerical data is that the profit of an enterprise equals its turnover minus its costs. Edits place restrictions on the imputations that are allowed and hence complicate the imputation process. In this paper we explore an adjustment approach. This adjustment approach consists of three steps. In the first step, the imputation step, nearest neighbour hot deck imputation is used to find several pre-imputed values. In a second step, the adjustment step, these pre-imputed values are adjusted so the resulting records satisfy all edits. In a third step, the best donor record is selected. The adjusted record corresponding to that donor record is the final imputed record. In principle, a potential donor that is not the closest to the record to be imputed may still give the best results after adjustment. In this paper we therefore focus on the number of potential donor records that are considered in the imputation step.Keywords: Nearest-neighbour Imputation, Edit restrictions, Linear programming, Data adjustment

AB - Item-nonresponse is often treated by means of an imputation technique. In some cases, the data have to satisfy certain constraints, which are frequently referred to as edits. An example of an edit for numerical data is that the profit of an enterprise equals its turnover minus its costs. Edits place restrictions on the imputations that are allowed and hence complicate the imputation process. In this paper we explore an adjustment approach. This adjustment approach consists of three steps. In the first step, the imputation step, nearest neighbour hot deck imputation is used to find several pre-imputed values. In a second step, the adjustment step, these pre-imputed values are adjusted so the resulting records satisfy all edits. In a third step, the best donor record is selected. The adjusted record corresponding to that donor record is the final imputed record. In principle, a potential donor that is not the closest to the record to be imputed may still give the best results after adjustment. In this paper we therefore focus on the number of potential donor records that are considered in the imputation step.Keywords: Nearest-neighbour Imputation, Edit restrictions, Linear programming, Data adjustment

M3 - Article

VL - 2017

SP - 47

EP - 59

JO - Romanian Statistical Review

JF - Romanian Statistical Review

SN - 1018-046X

IS - 3

ER -