Related Experiment Video
Updated: Jan 23, 2026

Generation of a Three-dimensional Full Thickness Skin Equivalent and Automated Wounding
Published on: February 26, 2015
Evaluating an Automated Number Series Item Generator Using Linear Logistic Test Models
Bao Sheng Loe1, Luning Sun2, Filip Simonfy3
1The Psychometrics Centre, Cambridge Judge Business School, University of Cambridge, Trumpington Street, Cambridge CB2 1AG, UK. bsl28@cam.ac.uk.
A new Automatic Number Series Item Generator (ANSIG) shows promise for creating tests. Cognitive operators significantly predict item difficulty, and generated items correlate well with ability tests.
Area of Science:
- Psychometrics
- Cognitive Psychology
- Educational Measurement
Background:
- Developing automated tools for generating psychometric tests is crucial for efficient assessment.
- Understanding the cognitive underpinnings of number series tasks is essential for test design.
Purpose of the Study:
- To evaluate the item properties of a novel Automatic Number Series Item Generator (ANSIG).
- To assess the construct validity and psychometric predictability of items generated by the ANSIG.
Main Methods:
- Utilized the numGen R package to develop 11 item models for the ANSIG.
- Employed Rasch Model and Linear Logistic Test Models (LLTM) for item parameter estimation.
- Administered a 16-item International Cognitive Ability Resource (ICAR) short form to assess construct validity.
Main Results:
- A single factor explained performance on tests using ANSIG-generated items.
- All hypothesized cognitive operators were significant predictors of item difficulty under the LLTM.
- Moderate to high correlations were found between ANSIG items and ICAR scores, particularly Letter-Numeric-Series items.
Conclusions:
- The ANSIG demonstrates potential for generating number series items with predictable psychometric properties.
- Cognitive operators are key predictors of item difficulty in automated test generation.
- Further research is needed to refine the automatic generation of item pools with desired psychometric characteristics.
More Related Videos
13:35Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring
Published on: June 13, 2025
08:34Automating ChIP-seq Experiments to Generate Epigenetic Profiles on 10,000 HeLa Cells
Published on: December 10, 2014
Related Concept Videos
Linear Circuits
Resistors In Series
In a series circuit, the...
Series Resonance
Linear Momentum
Linearization and Approximation
Application of Linearization and Approximation