Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Exploratory Item Classification Via Spectral Graph Clustering.

Yunxiao Chen¹, Xiaoou Li², Jingchen Liu³

¹Emory University, Atlanta, GA, USA.

Applied Psychological Measurement

|October 17, 2017

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Effect of Titrated Dexmedetomidine versus Esmolol on Postoperative Myocardial Injury in High-Risk Patients Undergoing Laparoscopic Colorectal Cancer Surgery: A Randomized Controlled Trial.

Drug design, development and therapy·2026

Same author

Incorporating external risk information with the Cox model under population heterogeneity: applications to trans-ancestry polygenic hazard scores.

Journal of the Royal Statistical Society. Series A, (Statistics in Society)·2026

Same author

Inflammatory Pseudotumor After Total Hip Arthroplasty-An Increasingly Recognized Complication.

Orthopaedic surgery·2026

Same author

A postoperative dynamic nomogram for predicting myocardial injury after noncardiac surgery in high-risk patients undergoing laparoscopic colorectal cancer resection.

BMC anesthesiology·2026

Same author

Thalamocortical regulation of prefrontal stability enables abstract rule generalization.

Science advances·2026

Same author

Therapeutic ultrasound in ophthalmology: a comprehensive review.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·2026

Same journal

The EM Algorithm and Its Variants in Cognitive Diagnostic Models: Comparing Their Propensity for Boundaries, Extremes, Convergence, and Suboptimal Solutions.

Applied psychological measurement·2026

Same journal

When Perceptions of Social Desirability Differ: Implications for the Multidimensional Nominal Response Model of Faking.

Applied psychological measurement·2026

Same journal

csemGT: An R Package for Estimating Raw-Score Conditional Standard Errors of Measurement in Generalizability Theory.

Applied psychological measurement·2026

Same journal

Confirmatory Factor Analysis with Adaptive Quadrature Estimator Using Four Link Functions.

Applied psychological measurement·2026

Same journal

Automatic Item Generation Measurement Models Respecting the Stochastic Sampling Space for Cross-Classified and Two-Level Sampling of Subjects and Incidentals.

Applied psychological measurement·2026

Same journal

Multistage Testing for Cognitive Diagnosis Based on Skill-Space Partitioning.

Applied psychological measurement·2026

See all related articles

This study introduces a spectral clustering algorithm for item analysis in large-scale assessments. It efficiently groups items, even with missing data, outperforming traditional methods in high-dimensional settings.

Area of Science:

Psychometrics
Computational Statistics
Graph Theory

Background:

Large-scale assessments require extensive item pools for accurate measurement.
Item clustering is crucial for test development, but traditional methods face computational challenges with high-dimensional data and missing responses.
Existing cluster analysis techniques like hierarchical clustering, K-means, and latent-class analysis can be computationally intensive and struggle with incomplete datasets.

Purpose of the Study:

To propose a novel spectral clustering algorithm for exploratory item cluster analysis.
To address the limitations of classical clustering methods in handling high-dimensional data and missing responses.
To offer a computationally efficient and effective alternative for item assignment in test development.

Main Methods:

Keywords:

Eysenck Personality Questionnaire cluster analysis large-scale assessment personality assessment spectral clustering

Related Experiment Videos

Development of a spectral clustering algorithm based on graph theory principles.
Construction of an item similarity graph to represent relationships among test items.
Extraction of item clusters by analyzing the graphical structure to group similar items.

Main Results:

The proposed spectral clustering algorithm demonstrates computational efficiency.
The method effectively handles datasets with missing or incomplete responses.
Simulations and an application to the Eysenck Personality Questionnaire indicate superior performance compared to traditional algorithms in high-dimensional contexts.

Conclusions:

Spectral clustering offers a powerful and efficient approach for exploratory item analysis.
This method overcomes key limitations of traditional clustering techniques, particularly for large-scale assessments with complex data.
The algorithm provides a valuable tool for improving the accuracy and efficiency of test development and psychometric analysis.