Passive imputation and parcel summaries are both valid to handle missing items in studies with many multi-item scales

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Previous studies showed that missing data in multi-item scales can best be handled by multiple imputation of item scores. However, when many scales are used, the number of items will become too large for the imputation model to reliably estimate imputations. A solution is to use passive imputation or a parcel summary score that combine and consequently reduce the number of variables in the imputation model. The performance of these methods was evaluated in a simulation study and illustrated in an example. Passive imputation, which updated scale scores from imputed items, and parcel summary scores that use the average over available item scores were compared to using all items simultaneously, imputing total scores of scales and complete-case analysis. Scale scores and coefficient estimates from linear regression were compared to “true” parameters on bias and precision. Passive imputation and using parcel summaries showed smaller bias and more precision than imputing total scores and complete-case analyses. Passive imputation or using parcel summary scores are valid missing data solutions in studies that include many multi-item scales.

Original languageEnglish
Pages (from-to)1128-1140
Number of pages13
JournalStatistical Methods in Medical Research
Volume27
Issue number4
DOIs
Publication statusPublished - 1 Apr 2018

Cite this

@article{42f96bf8aac84e5d97de50b7c01c6d14,
title = "Passive imputation and parcel summaries are both valid to handle missing items in studies with many multi-item scales",
abstract = "Previous studies showed that missing data in multi-item scales can best be handled by multiple imputation of item scores. However, when many scales are used, the number of items will become too large for the imputation model to reliably estimate imputations. A solution is to use passive imputation or a parcel summary score that combine and consequently reduce the number of variables in the imputation model. The performance of these methods was evaluated in a simulation study and illustrated in an example. Passive imputation, which updated scale scores from imputed items, and parcel summary scores that use the average over available item scores were compared to using all items simultaneously, imputing total scores of scales and complete-case analysis. Scale scores and coefficient estimates from linear regression were compared to “true” parameters on bias and precision. Passive imputation and using parcel summaries showed smaller bias and more precision than imputing total scores and complete-case analyses. Passive imputation or using parcel summary scores are valid missing data solutions in studies that include many multi-item scales.",
keywords = "item imputation, missing data, Multiple imputation, questionnaires, simulation study",
author = "Iris Eekhout and {de Vet}, {Henrica C.W.} and {de Boer}, {Michiel R.} and Twisk, {Jos W.R.} and Heymans, {Martijn W.}",
year = "2018",
month = "4",
day = "1",
doi = "10.1177/0962280216654511",
language = "English",
volume = "27",
pages = "1128--1140",
journal = "Statistical Methods in Medical Research",
issn = "0962-2802",
publisher = "SAGE Publications Ltd",
number = "4",

}

TY - JOUR

T1 - Passive imputation and parcel summaries are both valid to handle missing items in studies with many multi-item scales

AU - Eekhout, Iris

AU - de Vet, Henrica C.W.

AU - de Boer, Michiel R.

AU - Twisk, Jos W.R.

AU - Heymans, Martijn W.

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Previous studies showed that missing data in multi-item scales can best be handled by multiple imputation of item scores. However, when many scales are used, the number of items will become too large for the imputation model to reliably estimate imputations. A solution is to use passive imputation or a parcel summary score that combine and consequently reduce the number of variables in the imputation model. The performance of these methods was evaluated in a simulation study and illustrated in an example. Passive imputation, which updated scale scores from imputed items, and parcel summary scores that use the average over available item scores were compared to using all items simultaneously, imputing total scores of scales and complete-case analysis. Scale scores and coefficient estimates from linear regression were compared to “true” parameters on bias and precision. Passive imputation and using parcel summaries showed smaller bias and more precision than imputing total scores and complete-case analyses. Passive imputation or using parcel summary scores are valid missing data solutions in studies that include many multi-item scales.

AB - Previous studies showed that missing data in multi-item scales can best be handled by multiple imputation of item scores. However, when many scales are used, the number of items will become too large for the imputation model to reliably estimate imputations. A solution is to use passive imputation or a parcel summary score that combine and consequently reduce the number of variables in the imputation model. The performance of these methods was evaluated in a simulation study and illustrated in an example. Passive imputation, which updated scale scores from imputed items, and parcel summary scores that use the average over available item scores were compared to using all items simultaneously, imputing total scores of scales and complete-case analysis. Scale scores and coefficient estimates from linear regression were compared to “true” parameters on bias and precision. Passive imputation and using parcel summaries showed smaller bias and more precision than imputing total scores and complete-case analyses. Passive imputation or using parcel summary scores are valid missing data solutions in studies that include many multi-item scales.

KW - item imputation

KW - missing data

KW - Multiple imputation

KW - questionnaires

KW - simulation study

UR - http://www.scopus.com/inward/record.url?scp=85042849758&partnerID=8YFLogxK

U2 - 10.1177/0962280216654511

DO - 10.1177/0962280216654511

M3 - Article

VL - 27

SP - 1128

EP - 1140

JO - Statistical Methods in Medical Research

JF - Statistical Methods in Medical Research

SN - 0962-2802

IS - 4

ER -