Related Concept Videos
Factorial Design
Friedman Two-way Analysis of Variance by Ranks
Self-Report Tests of Personality
Response Surface Methodology
The process of RSM involves several key steps:
Theory of Attribution II: Kelley's Covariation Theory
Multiple Intelligences Theory
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Examining Differential Item Functioning from a Multidimensional IRT Perspective.
Testing linear hypotheses in repeated measures generalized linear models using external information.
Longitudinal Designs for Diagnostic Models: Identification and Estimation.
Related Experiment Video
Updated: Feb 26, 2026

Computerized Adaptive Testing System of Functional Assessment of Stroke
Published on: January 7, 2019
Examining Differential Item Functioning from a Multidimensional IRT Perspective.
1The University of Iowa.
Differential item functioning (DIF) occurs when test items measure different abilities. This study examines DIF using two-dimensional multidimensional item response theory (MIRT), offering insights into its causes and mitigation strategies.
More Related Videos
09:00Author Spotlight: Validation of SICOLE-R for Assessing Cognitive and Reading Skills in Spanish-Speaking Children and Its Role in Personalized Education
Published on: August 16, 2024
08:27Applying an eMASS Customization Program as a Research Tool to Evaluate Consumer Benefits
Published on: September 27, 2019
Area of Science:
- Psychometrics
- Educational Measurement
- Item Response Theory
Background:
- Differential item functioning (DIF) is a standard analysis in testing.
- DIF can arise when items measure different ability composites and groups have distinct ability distributions.
- Existing research highlights consequences of ignoring dimensionality in DIF analysis.
Purpose of the Study:
- To examine DIF from a two-dimensional multidimensional item response theory (MIRT) perspective.
- To illustrate the compensatory MIRT model and graphical representation of items and composites.
- To investigate three MIRT-based approaches for understanding DIF.
Main Methods:
- Utilizing a two-dimensional multidimensional item response theory (MIRT) framework.
- Reviewing analytical research on the consequences of unidimensional IRT models for two-dimensional data.
- Investigating uniform/nonuniform DIF with differing ability distributions, accounting for the full latent ability space, and scenario-based DIF.
Main Results:
- Item parameters can vary based on latent ability distributions.
- Ignoring dimensionality in IRT models can lead to inaccurate DIF detection.
- Considering the complete latent ability space helps mitigate DIF effects.
- Differing problem-solving approaches can cause DIF even with identical distributions.
Conclusions:
- A two-dimensional MIRT perspective provides a robust framework for understanding DIF.
- Accurate DIF analysis requires considering the full latent ability space and potential scenario-based causes.
- Identifying the root causes of DIF in flagged items remains a critical challenge.