Extensions to Mean–Geometric Mean Linking

Mean-geometric mean (MGM) linking is a widely used method for linking two groups within the two-parameter logistic (2PL) item response model. However, the presence of differential item functioning (DIF) can lead to biased parameter estimates using the traditional MGM method. To address this, alterna...

Full description

Saved in:
Bibliographic Details
Main Author: Alexander Robitzsch
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/1/35
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mean-geometric mean (MGM) linking is a widely used method for linking two groups within the two-parameter logistic (2PL) item response model. However, the presence of differential item functioning (DIF) can lead to biased parameter estimates using the traditional MGM method. To address this, alternative linking methods based on robust loss functions have been proposed. In this article, the conventional <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mn>2</mn></msub></semantics></math></inline-formula> loss function is compared with the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mrow><mn>0.5</mn></mrow></msub></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mn>0</mn></msub></semantics></math></inline-formula> loss functions in MGM linking. Our results suggest that robust loss functions are preferable when dealing with outlying DIF effects, with the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mn>0</mn></msub></semantics></math></inline-formula> function showing particular advantages in tests with larger item sets and sample sizes. Additionally, a simulation study demonstrates that defining MGM linking based on item intercepts rather than item difficulties leads to more accurate linking parameter estimates. Finally, robust Haberman linking slightly outperforms robust MGM linking in two-group comparisons.
ISSN:2227-7390