Latent variable models for harmonization of test scores: a case study on memory

Edwin R. van den Heuvel (Corresponding author), Lauren E. Griffith, Nazmul Sohel, Isabel Fortier, Graciela Muniz-Terrera, Parminder Raina

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

1 Downloads (Pure)

Uittreksel

Combining data from different studies has a long tradition within the scientific community. It requires that the same information is collected from each study to be able to pool individual data. When studies have implemented different methods or used different instruments (e.g., questionnaires) for measuring the same characteristics or constructs, the observed variables need to be harmonized in some way to obtain equivalent content information across studies. This paper formulates the main concepts for harmonizing test scores from different observational studies in terms of latent variable models. The concepts are formulated in terms of calibration, invariance, and exchangeability. Although similar ideas are present in measurement reliability and test equating, harmonization is different from measurement invariance and generalizes test equating. In addition, if a test score needs to be transformed to another test score, harmonization of variables is only possible under specific conditions. Observed test scores that connect all of the different studies, are necessary to be able to test the underlying assumptions of harmonization. The concepts of harmonization are illustrated on multiple memory test scores from three different Canadian studies.

Originele taal-2Engels
Pagina's (van-tot)34-52
Aantal pagina's19
TijdschriftBiometrical Journal
Volume62
Nummer van het tijdschrift1
Vroegere onlinedatum4 okt 2019
DOI's
StatusGepubliceerd - jan 2020

Vingerafdruk

Latent Variable Models
Score Test
Measurement Invariance
Exchangeability
Observational Study
Information Content
Questionnaire
Invariance
Calibration
Latent variable models
Harmonization
Test scores
Generalise
Necessary
Concepts

Citeer dit

van den Heuvel, Edwin R. ; Griffith, Lauren E. ; Sohel, Nazmul ; Fortier, Isabel ; Muniz-Terrera, Graciela ; Raina, Parminder. / Latent variable models for harmonization of test scores : a case study on memory. In: Biometrical Journal. 2020 ; Vol. 62, Nr. 1. blz. 34-52.
@article{10967ebaecc14233a6f45d5a9362ae79,
title = "Latent variable models for harmonization of test scores: a case study on memory",
abstract = "Combining data from different studies has a long tradition within the scientific community. It requires that the same information is collected from each study to be able to pool individual data. When studies have implemented different methods or used different instruments (e.g., questionnaires) for measuring the same characteristics or constructs, the observed variables need to be harmonized in some way to obtain equivalent content information across studies. This paper formulates the main concepts for harmonizing test scores from different observational studies in terms of latent variable models. The concepts are formulated in terms of calibration, invariance, and exchangeability. Although similar ideas are present in measurement reliability and test equating, harmonization is different from measurement invariance and generalizes test equating. In addition, if a test score needs to be transformed to another test score, harmonization of variables is only possible under specific conditions. Observed test scores that connect all of the different studies, are necessary to be able to test the underlying assumptions of harmonization. The concepts of harmonization are illustrated on multiple memory test scores from three different Canadian studies.",
keywords = "agreement, content equivalence, factorial invariance, harmonization, individual participants data, latent variable models, measurement reliability, meta-analysis",
author = "{van den Heuvel}, {Edwin R.} and Griffith, {Lauren E.} and Nazmul Sohel and Isabel Fortier and Graciela Muniz-Terrera and Parminder Raina",
year = "2020",
month = "1",
doi = "10.1002/bimj.201800146",
language = "English",
volume = "62",
pages = "34--52",
journal = "Biometrical Journal",
issn = "0323-3847",
publisher = "Wiley-VCH Verlag",
number = "1",

}

van den Heuvel, ER, Griffith, LE, Sohel, N, Fortier, I, Muniz-Terrera, G & Raina, P 2020, 'Latent variable models for harmonization of test scores: a case study on memory', Biometrical Journal, vol. 62, nr. 1, blz. 34-52. https://doi.org/10.1002/bimj.201800146

Latent variable models for harmonization of test scores : a case study on memory. / van den Heuvel, Edwin R. (Corresponding author); Griffith, Lauren E.; Sohel, Nazmul; Fortier, Isabel; Muniz-Terrera, Graciela; Raina, Parminder.

In: Biometrical Journal, Vol. 62, Nr. 1, 01.2020, blz. 34-52.

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

TY - JOUR

T1 - Latent variable models for harmonization of test scores

T2 - a case study on memory

AU - van den Heuvel, Edwin R.

AU - Griffith, Lauren E.

AU - Sohel, Nazmul

AU - Fortier, Isabel

AU - Muniz-Terrera, Graciela

AU - Raina, Parminder

PY - 2020/1

Y1 - 2020/1

N2 - Combining data from different studies has a long tradition within the scientific community. It requires that the same information is collected from each study to be able to pool individual data. When studies have implemented different methods or used different instruments (e.g., questionnaires) for measuring the same characteristics or constructs, the observed variables need to be harmonized in some way to obtain equivalent content information across studies. This paper formulates the main concepts for harmonizing test scores from different observational studies in terms of latent variable models. The concepts are formulated in terms of calibration, invariance, and exchangeability. Although similar ideas are present in measurement reliability and test equating, harmonization is different from measurement invariance and generalizes test equating. In addition, if a test score needs to be transformed to another test score, harmonization of variables is only possible under specific conditions. Observed test scores that connect all of the different studies, are necessary to be able to test the underlying assumptions of harmonization. The concepts of harmonization are illustrated on multiple memory test scores from three different Canadian studies.

AB - Combining data from different studies has a long tradition within the scientific community. It requires that the same information is collected from each study to be able to pool individual data. When studies have implemented different methods or used different instruments (e.g., questionnaires) for measuring the same characteristics or constructs, the observed variables need to be harmonized in some way to obtain equivalent content information across studies. This paper formulates the main concepts for harmonizing test scores from different observational studies in terms of latent variable models. The concepts are formulated in terms of calibration, invariance, and exchangeability. Although similar ideas are present in measurement reliability and test equating, harmonization is different from measurement invariance and generalizes test equating. In addition, if a test score needs to be transformed to another test score, harmonization of variables is only possible under specific conditions. Observed test scores that connect all of the different studies, are necessary to be able to test the underlying assumptions of harmonization. The concepts of harmonization are illustrated on multiple memory test scores from three different Canadian studies.

KW - agreement

KW - content equivalence

KW - factorial invariance

KW - harmonization

KW - individual participants data

KW - latent variable models

KW - measurement reliability

KW - meta-analysis

UR - http://www.scopus.com/inward/record.url?scp=85073962444&partnerID=8YFLogxK

U2 - 10.1002/bimj.201800146

DO - 10.1002/bimj.201800146

M3 - Article

C2 - 31583767

AN - SCOPUS:85073962444

VL - 62

SP - 34

EP - 52

JO - Biometrical Journal

JF - Biometrical Journal

SN - 0323-3847

IS - 1

ER -