Publication

Model selection in continuous test norming with GAMLSS

Voncken, L., Albers, C. & Timmerman, M., Oct-2019, In : Assessment. 26, 7, p. 1329-1346 18 p.

Research output: Contribution to journalArticleAcademicpeer-review

APA

Voncken, L., Albers, C., & Timmerman, M. (2019). Model selection in continuous test norming with GAMLSS. Assessment, 26(7), 1329-1346. https://doi.org/10.1177/1073191117715113

Author

Voncken, Lieke ; Albers, Casper ; Timmerman, Marieke. / Model selection in continuous test norming with GAMLSS. In: Assessment. 2019 ; Vol. 26, No. 7. pp. 1329-1346.

Harvard

Voncken, L, Albers, C & Timmerman, M 2019, 'Model selection in continuous test norming with GAMLSS', Assessment, vol. 26, no. 7, pp. 1329-1346. https://doi.org/10.1177/1073191117715113

Standard

Model selection in continuous test norming with GAMLSS. / Voncken, Lieke; Albers, Casper; Timmerman, Marieke.

In: Assessment, Vol. 26, No. 7, 10.2019, p. 1329-1346.

Research output: Contribution to journalArticleAcademicpeer-review

Vancouver

Voncken L, Albers C, Timmerman M. Model selection in continuous test norming with GAMLSS. Assessment. 2019 Oct;26(7):1329-1346. https://doi.org/10.1177/1073191117715113


BibTeX

@article{02beadeb5f394be981516a836172ced9,
title = "Model selection in continuous test norming with GAMLSS",
abstract = "To compute norms from reference group test scores, continuous norming is preferred over traditional norming. A suitable continuous norming approach for continuous data is the use of the Box–Cox Power Exponential model, which is found in the generalized additive models for location, scale, and shape. Applying the Box–Cox Power Exponential model for test norming requires model selection, but it is unknown how well this can be done with an automatic selection procedure. In a simulation study, we compared the performance of two stepwise model selection procedures combined with four model-fit criteria (Akaike information criterion, Bayesian information criterion, generalized Akaike information criterion (3), cross-validation), varying data complexity, sampling design, and sample size in a fully crossed design. The new procedure combined with one of the generalized Akaike information criterion was the most efficient model selection procedure (i.e., required the smallest sample size). The advocated model selection procedure is illustrated with norming data of an intelligence test.",
keywords = "CENTILE CURVES, REGRESSION, SPIROMETRY, AGE",
author = "Lieke Voncken and Casper Albers and Marieke Timmerman",
year = "2019",
month = "10",
doi = "10.1177/1073191117715113",
language = "English",
volume = "26",
pages = "1329--1346",
journal = "Assessment",
issn = "1073-1911",
number = "7",

}

RIS

TY - JOUR

T1 - Model selection in continuous test norming with GAMLSS

AU - Voncken, Lieke

AU - Albers, Casper

AU - Timmerman, Marieke

PY - 2019/10

Y1 - 2019/10

N2 - To compute norms from reference group test scores, continuous norming is preferred over traditional norming. A suitable continuous norming approach for continuous data is the use of the Box–Cox Power Exponential model, which is found in the generalized additive models for location, scale, and shape. Applying the Box–Cox Power Exponential model for test norming requires model selection, but it is unknown how well this can be done with an automatic selection procedure. In a simulation study, we compared the performance of two stepwise model selection procedures combined with four model-fit criteria (Akaike information criterion, Bayesian information criterion, generalized Akaike information criterion (3), cross-validation), varying data complexity, sampling design, and sample size in a fully crossed design. The new procedure combined with one of the generalized Akaike information criterion was the most efficient model selection procedure (i.e., required the smallest sample size). The advocated model selection procedure is illustrated with norming data of an intelligence test.

AB - To compute norms from reference group test scores, continuous norming is preferred over traditional norming. A suitable continuous norming approach for continuous data is the use of the Box–Cox Power Exponential model, which is found in the generalized additive models for location, scale, and shape. Applying the Box–Cox Power Exponential model for test norming requires model selection, but it is unknown how well this can be done with an automatic selection procedure. In a simulation study, we compared the performance of two stepwise model selection procedures combined with four model-fit criteria (Akaike information criterion, Bayesian information criterion, generalized Akaike information criterion (3), cross-validation), varying data complexity, sampling design, and sample size in a fully crossed design. The new procedure combined with one of the generalized Akaike information criterion was the most efficient model selection procedure (i.e., required the smallest sample size). The advocated model selection procedure is illustrated with norming data of an intelligence test.

KW - CENTILE CURVES

KW - REGRESSION

KW - SPIROMETRY

KW - AGE

U2 - 10.1177/1073191117715113

DO - 10.1177/1073191117715113

M3 - Article

VL - 26

SP - 1329

EP - 1346

JO - Assessment

JF - Assessment

SN - 1073-1911

IS - 7

ER -

ID: 42035139