Estimating the number of serious road injuries per vehicle type in the Netherlands by using multiple imputation of latent classes

Laura Boeschoten*, Ton de Waal, Jeroen Vermunt

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

2 Downloads (Pure)

Abstract

Statistics that are published by official agencies are often generated by using population registries, which are likely to contain classification errors and missing values. A method that simultaneously handles classification errors and missing values is multiple imputation of latent classes (MILC). We apply the MILC method to estimate the number of serious road injuries per vehicle type in the Netherlands and to stratify the number of serious road injuries per vehicle type into relevant subgroups by using data from two registries. For this specific application, the MILC method is extended to handle the large number of missing values in the stratification variable ‘region of accident’ and to include more stratification covariates. After applying the extended MILC method, a multiply imputed data set is generated that can be used to create statistical figures in a straightforward manner, and that incorporates uncertainty due to classification errors and missing values in the estimate of the total variance.
Original languageEnglish
Pages (from-to)1463-1486
JournalJournal of the Royal Statistical Society A
Volume182
Issue number4
DOIs
Publication statusPublished - 2019

Fingerprint

Accidents
Statistics
Uncertainty

Keywords

  • Classification error
  • Combined data set
  • Latent class analysis
  • MODELS
  • Missing values
  • Multiple imputation

Cite this

@article{93489b36e982447198b2e3fe244dfd01,
title = "Estimating the number of serious road injuries per vehicle type in the Netherlands by using multiple imputation of latent classes",
abstract = "Statistics that are published by official agencies are often generated by using population registries, which are likely to contain classification errors and missing values. A method that simultaneously handles classification errors and missing values is multiple imputation of latent classes (MILC). We apply the MILC method to estimate the number of serious road injuries per vehicle type in the Netherlands and to stratify the number of serious road injuries per vehicle type into relevant subgroups by using data from two registries. For this specific application, the MILC method is extended to handle the large number of missing values in the stratification variable ‘region of accident’ and to include more stratification covariates. After applying the extended MILC method, a multiply imputed data set is generated that can be used to create statistical figures in a straightforward manner, and that incorporates uncertainty due to classification errors and missing values in the estimate of the total variance.",
keywords = "Classification error, Combined data set, Latent class analysis, MODELS, Missing values, Multiple imputation",
author = "Laura Boeschoten and {de Waal}, Ton and Jeroen Vermunt",
year = "2019",
doi = "10.1111/rssa.12471",
language = "English",
volume = "182",
pages = "1463--1486",
journal = "Journal of the Royal Statistical Society A",
number = "4",

}

Estimating the number of serious road injuries per vehicle type in the Netherlands by using multiple imputation of latent classes. / Boeschoten, Laura; de Waal, Ton; Vermunt, Jeroen.

In: Journal of the Royal Statistical Society A, Vol. 182, No. 4, 2019, p. 1463-1486.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Estimating the number of serious road injuries per vehicle type in the Netherlands by using multiple imputation of latent classes

AU - Boeschoten, Laura

AU - de Waal, Ton

AU - Vermunt, Jeroen

PY - 2019

Y1 - 2019

N2 - Statistics that are published by official agencies are often generated by using population registries, which are likely to contain classification errors and missing values. A method that simultaneously handles classification errors and missing values is multiple imputation of latent classes (MILC). We apply the MILC method to estimate the number of serious road injuries per vehicle type in the Netherlands and to stratify the number of serious road injuries per vehicle type into relevant subgroups by using data from two registries. For this specific application, the MILC method is extended to handle the large number of missing values in the stratification variable ‘region of accident’ and to include more stratification covariates. After applying the extended MILC method, a multiply imputed data set is generated that can be used to create statistical figures in a straightforward manner, and that incorporates uncertainty due to classification errors and missing values in the estimate of the total variance.

AB - Statistics that are published by official agencies are often generated by using population registries, which are likely to contain classification errors and missing values. A method that simultaneously handles classification errors and missing values is multiple imputation of latent classes (MILC). We apply the MILC method to estimate the number of serious road injuries per vehicle type in the Netherlands and to stratify the number of serious road injuries per vehicle type into relevant subgroups by using data from two registries. For this specific application, the MILC method is extended to handle the large number of missing values in the stratification variable ‘region of accident’ and to include more stratification covariates. After applying the extended MILC method, a multiply imputed data set is generated that can be used to create statistical figures in a straightforward manner, and that incorporates uncertainty due to classification errors and missing values in the estimate of the total variance.

KW - Classification error

KW - Combined data set

KW - Latent class analysis

KW - MODELS

KW - Missing values

KW - Multiple imputation

U2 - 10.1111/rssa.12471

DO - 10.1111/rssa.12471

M3 - Article

VL - 182

SP - 1463

EP - 1486

JO - Journal of the Royal Statistical Society A

JF - Journal of the Royal Statistical Society A

IS - 4

ER -