Related Experiment Video
Updated: Oct 25, 2025
09:43
The 5-Choice Serial Reaction Time Task: A Task of Attention and Impulse Control for Rodents
Published on: August 10, 2014
46.4K
A Mixture Response Time Process Model for Aberrant Behaviors and Item Nonresponses.
Jing Lu1, Chun Wang2, Ningzhong Shi1
1Key Laboratory of Applied Statistics of MOE, School of Mathematics and Statistics, Northeast Normal University, Changchun, Jilin, China.
Multivariate Behavioral Research
|August 6, 2021
Summary
This study introduces a new model to detect rapid guessing and cheating behaviors in standardized tests. It also accounts for item nonresponses, improving accuracy in test analysis.
Area of Science:
- Psychometrics
- Educational Measurement
- Data Science
Background:
- Standardized tests often involve time limits, leading to varied examinee behaviors.
- Item nonresponses (omitted or not-reached) are common and related to latent abilities.
- Distinguishing between normal and aberrant behaviors like rapid guessing and cheating is crucial.
Purpose of the Study:
- To propose an innovative mixture response time process model.
- To detect rapid guessing and cheating behaviors in examinees.
- To account for not-reached and omitted item nonresponses.
Main Methods:
- A two-stage approach combining existing models (Wang et al., 2018; Lu & Wang, 2020).
- Stage 1: Fitting a mixture response time process model to responses and response times.
- Stage 2: Employing a Bayesian residual index to differentiate aberrant behaviors.
Main Results:
- Simulation results demonstrate accurate item and person parameter estimation.
- The proposed method shows high detection rates for aberrant behaviors.
- The model effectively accounts for the missing data mechanism.
Conclusions:
- The novel two-stage model accurately identifies aberrant behaviors and handles item nonresponses.
- This method offers improved accuracy in standardized test analysis.
- The approach has practical applications in real-world data analysis.
