Standard

A review of different scaling approaches under full invariance, partial invariance, and noninvariance for cross-sectional country comparisons in large-scale assessments. / Robitzsch, Alexander; Lüdtke, Oliver.

in: Psychological Test and Assessment Modeling, Jahrgang 62, Nr. 2, 06.2020, S. 233-279.

Publikationen: Beitrag in FachzeitschriftArtikel in FachzeitschriftForschungBegutachtung

Harvard

APA

Vancouver

Author

BibTeX

@article{42bed0df7b5c4c18bad994e4cadd9aed,
title = "A review of different scaling approaches under full invariance, partial invariance, and noninvariance for cross-sectional country comparisons in large-scale assessments",
abstract = "One of the primary goals of international large-scale assessments (ILSAs) in education is the comparison of country means in student achievement. The present article introduces a framework for discussing differential item functioning (DIF) for country comparisons in ILSAs. Three different linking methods are compared: concurrent calibration based on full invariance, concurrent calibration based on partial invariance using the MD or RMSD statistics, and separate calibration with subsequent nonrobust and robust linking approaches. Furthermore, we show analytically the bias in country means of different linking methods in the presence of DIF. In a simulation study, we show that partial invariance and robust linking approaches provide less biased country mean estimates than the full invariance approach in the case of biased items. Some guidelines are derived for the selection of cutoff values for the MD and RMSD statistics in the partial invariance approach.",
keywords = "Methodological research and development, international large-scale assessments, linking, differential item functioning, multiple groups, RMSD statistic",
author = "Alexander Robitzsch and Oliver L{\"u}dtke",
year = "2020",
month = jun,
language = "English",
volume = "62",
pages = "233--279",
journal = "Psychological Test and Assessment Modeling",
issn = "1614-9947",
publisher = "Pabst Science Publ. ",
number = "2",

}

RIS

TY - JOUR

T1 - A review of different scaling approaches under full invariance, partial invariance, and noninvariance for cross-sectional country comparisons in large-scale assessments

AU - Robitzsch, Alexander

AU - Lüdtke, Oliver

PY - 2020/6

Y1 - 2020/6

N2 - One of the primary goals of international large-scale assessments (ILSAs) in education is the comparison of country means in student achievement. The present article introduces a framework for discussing differential item functioning (DIF) for country comparisons in ILSAs. Three different linking methods are compared: concurrent calibration based on full invariance, concurrent calibration based on partial invariance using the MD or RMSD statistics, and separate calibration with subsequent nonrobust and robust linking approaches. Furthermore, we show analytically the bias in country means of different linking methods in the presence of DIF. In a simulation study, we show that partial invariance and robust linking approaches provide less biased country mean estimates than the full invariance approach in the case of biased items. Some guidelines are derived for the selection of cutoff values for the MD and RMSD statistics in the partial invariance approach.

AB - One of the primary goals of international large-scale assessments (ILSAs) in education is the comparison of country means in student achievement. The present article introduces a framework for discussing differential item functioning (DIF) for country comparisons in ILSAs. Three different linking methods are compared: concurrent calibration based on full invariance, concurrent calibration based on partial invariance using the MD or RMSD statistics, and separate calibration with subsequent nonrobust and robust linking approaches. Furthermore, we show analytically the bias in country means of different linking methods in the presence of DIF. In a simulation study, we show that partial invariance and robust linking approaches provide less biased country mean estimates than the full invariance approach in the case of biased items. Some guidelines are derived for the selection of cutoff values for the MD and RMSD statistics in the partial invariance approach.

KW - Methodological research and development

KW - international large-scale assessments

KW - linking

KW - differential item functioning

KW - multiple groups

KW - RMSD statistic

M3 - Journal article

VL - 62

SP - 233

EP - 279

JO - Psychological Test and Assessment Modeling

JF - Psychological Test and Assessment Modeling

SN - 1614-9947

IS - 2

ER -

ID: 1400685