Modeling Conditional Dependence of Response Accuracy and Response Time with the Diffusion Item Response Theory Model

Area of Science:

• Cognitive Psychology
• Psychometrics
• Mathematical Psychology

Background:

• Conditional dependence between response accuracy and response time (RT) is a key phenomenon in psychometrics.
• Existing diffusion IRT models provide a framework but lack the ability to fully capture complex behavioral patterns.
• Understanding individual differences in cognitive processes is crucial for accurate modeling.

Purpose of the Study:

• To propose an extended diffusion IRT model incorporating person and item variability in cognitive capacity and starting points.
• To investigate how these variability components explain observed conditional dependency patterns.
• To provide a flexible model for analyzing the interplay between response accuracy, RT, and individual differences.

Main Methods:

• Development of an extended diffusion IRT model.
• Introduction of variability in drift rate (cognitive capacity) and starting point parameters.
• Validation through a simulation study for parameter recovery and two empirical applications.

Main Results:

• The extended model successfully explains positive and negative conditional dependency, interacting with item difficulty.
• Variability in cognitive capacity predicts these dependency patterns.
• Variability in starting points accounts for early changes in accuracy as a function of RT, producing curvilinear accuracy functions.

Conclusions:

• The proposed extended diffusion IRT model offers a more comprehensive account of conditional accuracy functions.
• Incorporating variability in cognitive capacity and starting points is essential for understanding response accuracy and RT relationships.
• The model provides a valuable tool for psychometric research and applied data analysis.