Estimating error rates in an administrative register and survey questions using a latent class model

D.L. Oberski

Research output: Chapter in Book/Report/Conference proceedingChapterScientific

Abstract

Administrative data obtained from government registers provide a wealth of potential for the social sciences. Administrative registers may contain considerable measurement errors, including definition, reporting, timing, processing, editing, linkage, and coverage errors. This chapter explores how to estimate the extent of measurement errors in both administrative register data and survey answers. It demonstrates one approach to doing so: latent variable modeling. Modeling these mode effects allows for the identification of both random classification errors and method effects without the need for multiple “traits” (true values). It could therefore be termed a “single-trait-multimethod” (STMM) approach. The chapter describes the data on neighborhood of residence obtained from a survey and an important Dutch official administrative register, and then details the latent class model built to estimate classification error rates in these measures. The costs of full-scale audits compared with latent variable modeling are gigantic, meaning that a small inaccuracy still leaves latent variable modeling an attractive alternative.
Original languageEnglish
Title of host publicationTotal survey error
EditorsP. Biemer, B. West, S. Eckman, B. Edwards, C. Tucker
Place of PublicationNew York
PublisherWiley
Number of pages14
DOIs
Publication statusPublished - 2015

Fingerprint

audit
social science
coverage
costs
Values

Cite this

Oberski, D. L. (2015). Estimating error rates in an administrative register and survey questions using a latent class model. In P. Biemer, B. West, S. Eckman, B. Edwards, & C. Tucker (Eds.), Total survey error New York: Wiley. https://doi.org/10.1002/9781119041702.ch16
Oberski, D.L. / Estimating error rates in an administrative register and survey questions using a latent class model. Total survey error. editor / P. Biemer ; B. West ; S. Eckman ; B. Edwards ; C. Tucker. New York : Wiley, 2015.
@inbook{606f7d90375c4d76aa374f7754a33fc2,
title = "Estimating error rates in an administrative register and survey questions using a latent class model",
abstract = "Administrative data obtained from government registers provide a wealth of potential for the social sciences. Administrative registers may contain considerable measurement errors, including definition, reporting, timing, processing, editing, linkage, and coverage errors. This chapter explores how to estimate the extent of measurement errors in both administrative register data and survey answers. It demonstrates one approach to doing so: latent variable modeling. Modeling these mode effects allows for the identification of both random classification errors and method effects without the need for multiple “traits” (true values). It could therefore be termed a “single-trait-multimethod” (STMM) approach. The chapter describes the data on neighborhood of residence obtained from a survey and an important Dutch official administrative register, and then details the latent class model built to estimate classification error rates in these measures. The costs of full-scale audits compared with latent variable modeling are gigantic, meaning that a small inaccuracy still leaves latent variable modeling an attractive alternative.",
author = "D.L. Oberski",
year = "2015",
doi = "10.1002/9781119041702.ch16",
language = "English",
editor = "Biemer, {P. } and B. West and Eckman, {S. } and B. Edwards and C. Tucker",
booktitle = "Total survey error",
publisher = "Wiley",

}

Oberski, DL 2015, Estimating error rates in an administrative register and survey questions using a latent class model. in P Biemer, B West, S Eckman, B Edwards & C Tucker (eds), Total survey error. Wiley, New York. https://doi.org/10.1002/9781119041702.ch16

Estimating error rates in an administrative register and survey questions using a latent class model. / Oberski, D.L.

Total survey error. ed. / P. Biemer; B. West; S. Eckman; B. Edwards; C. Tucker. New York : Wiley, 2015.

Research output: Chapter in Book/Report/Conference proceedingChapterScientific

TY - CHAP

T1 - Estimating error rates in an administrative register and survey questions using a latent class model

AU - Oberski, D.L.

PY - 2015

Y1 - 2015

N2 - Administrative data obtained from government registers provide a wealth of potential for the social sciences. Administrative registers may contain considerable measurement errors, including definition, reporting, timing, processing, editing, linkage, and coverage errors. This chapter explores how to estimate the extent of measurement errors in both administrative register data and survey answers. It demonstrates one approach to doing so: latent variable modeling. Modeling these mode effects allows for the identification of both random classification errors and method effects without the need for multiple “traits” (true values). It could therefore be termed a “single-trait-multimethod” (STMM) approach. The chapter describes the data on neighborhood of residence obtained from a survey and an important Dutch official administrative register, and then details the latent class model built to estimate classification error rates in these measures. The costs of full-scale audits compared with latent variable modeling are gigantic, meaning that a small inaccuracy still leaves latent variable modeling an attractive alternative.

AB - Administrative data obtained from government registers provide a wealth of potential for the social sciences. Administrative registers may contain considerable measurement errors, including definition, reporting, timing, processing, editing, linkage, and coverage errors. This chapter explores how to estimate the extent of measurement errors in both administrative register data and survey answers. It demonstrates one approach to doing so: latent variable modeling. Modeling these mode effects allows for the identification of both random classification errors and method effects without the need for multiple “traits” (true values). It could therefore be termed a “single-trait-multimethod” (STMM) approach. The chapter describes the data on neighborhood of residence obtained from a survey and an important Dutch official administrative register, and then details the latent class model built to estimate classification error rates in these measures. The costs of full-scale audits compared with latent variable modeling are gigantic, meaning that a small inaccuracy still leaves latent variable modeling an attractive alternative.

U2 - 10.1002/9781119041702.ch16

DO - 10.1002/9781119041702.ch16

M3 - Chapter

BT - Total survey error

A2 - Biemer, P.

A2 - West, B.

A2 - Eckman, S.

A2 - Edwards, B.

A2 - Tucker, C.

PB - Wiley

CY - New York

ER -

Oberski DL. Estimating error rates in an administrative register and survey questions using a latent class model. In Biemer P, West B, Eckman S, Edwards B, Tucker C, editors, Total survey error. New York: Wiley. 2015 https://doi.org/10.1002/9781119041702.ch16