Measurement invariance in factor analytic and item response theory framework

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F23%3A00580475" target="_blank" >RIV/67985807:_____/23:00580475 - isvavai.cz</a>

Výsledek na webu

<a href="https://eam2023.ugent.be/images/eam2023_abstracts_book.pdf" target="_blank" >https://eam2023.ugent.be/images/eam2023_abstracts_book.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Measurement invariance in factor analytic and item response theory framework

Popis výsledku v původním jazyce

ZÁKLADNÍ ÚDAJE: The 10th European Congress of Methodology (EAM2023) Book of Abstracts. Ghent: Ghent University, 2023. s. 193-193. [EAM2023: European Congress of Methodology /10./. 11.07.2023-13.07.2023, Ghent]. ABSTRAKT: The relations between binary factor analysis (FA) model and 2-parameter item response theory (IRT) model were established some time ago (Takane & de Leeuw 1987, Kamata & Bauer 2008). However, when accounting for multiple groups and testing for between-group differences on an item level, the methods based on FA and IRT frameworks are usually considered supplementary rather than equivalent. This work focuses on relations between FA models used for testing measurement invariance and IRT models used for testing differential item functioning (DIF). We focus on equivalence of the two types of group-specific models under a set of conditions. Different types of invariance are discussed, namely configural, weak (metric), strong (scalar), and partial, together with models testing for non-uniform DIF, uniform DIF, and no DIF in all items, respectively. Computational aspects and extensions to multiple groups and ordinal items are considered. A real data example is provided to demonstrate the presented relations.

Název v anglickém jazyce

Measurement invariance in factor analytic and item response theory framework

Popis výsledku anglicky

ZÁKLADNÍ ÚDAJE: The 10th European Congress of Methodology (EAM2023) Book of Abstracts. Ghent: Ghent University, 2023. s. 193-193. [EAM2023: European Congress of Methodology /10./. 11.07.2023-13.07.2023, Ghent]. ABSTRAKT: The relations between binary factor analysis (FA) model and 2-parameter item response theory (IRT) model were established some time ago (Takane & de Leeuw 1987, Kamata & Bauer 2008). However, when accounting for multiple groups and testing for between-group differences on an item level, the methods based on FA and IRT frameworks are usually considered supplementary rather than equivalent. This work focuses on relations between FA models used for testing measurement invariance and IRT models used for testing differential item functioning (DIF). We focus on equivalence of the two types of group-specific models under a set of conditions. Different types of invariance are discussed, namely configural, weak (metric), strong (scalar), and partial, together with models testing for non-uniform DIF, uniform DIF, and no DIF in all items, respectively. Computational aspects and extensions to multiple groups and ordinal items are considered. A real data example is provided to demonstrate the presented relations.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

<a href="/cs/project/GA21-03658S" target="_blank" >GA21-03658S: Teoretické základy výpočetní psychometrie</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů