Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Maximum information stratification method for controlling item exposure in computerized adaptive testing.

Juan Ramón Barrada1, Paloma Mazuela, Julio Olea

  • 1Facultad de Psicología, Universidad Autónoma de Madrid, Spain. juanra.barrada@uam.es

Psicothema
|February 14, 2007
PubMed
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

The Impact of Social Media Disorder, Family Functioning, and Community Social Disorder on Adolescents' Psychological Distress: The Mediating Role of Intolerance to Uncertainty.

Children (Basel, Switzerland)·2025
Same author

Untangling the role of emotion regulation in gambling and video gaming cravings: A replication and extension study.

Addictive behaviors·2025
Same author

Unveiling the association between chronotype and emotional eating in Spanish adolescents: The EHDLA study.

Appetite·2025
Same author

What role do orthorectic beliefs play in orthorexia nervosa and healthy orthorexia? Development and validation of the Orthorexia Beliefs Scale (OBS).

Appetite·2025
Same author

Comment on Rodríguez-Cortés et al. Individual Circadian Preference, Eating Disorders and Obesity in Children and Adolescents: A Dangerous Liaison? A Systematic Review and a Meta-Analysis. <i>Children</i> 2022, <i>9</i>, 167.

Children (Basel, Switzerland)·2024
Same author

Differentiating healthy orthorexia from orthorexia nervosa: sociodemographic, psychological and dietary characteristics in a French sample.

Public health nutrition·2024
Same journal

Personal Recovery in Addictions: Development of a new Assessment Instrument.

Psicothema·2026
Same journal

Internet Habits, Problematic Internet Use, and Online Risk Practices Among Adolescents With ADHD in Spain.

Psicothema·2026
Same journal

Relationship Between Social Connectedness and Quality of Life in Older Adults: An Examination of Sex Differences.

Psicothema·2026
Same journal

The Influence of Gender on Measuring Mental Health Stigma. A Cross-Sectional Vignette Study With the Attribution Questionnaire 9.

Psicothema·2026
Same journal

Comprehensive Assessment of Mental Health Stigma.

Psicothema·2026
Same journal

Psychometric Properties of the Teachers' Responses to Bullying Questionnaire (TRBQ) in Spanish Students.

Psicothema·2026
See all related articles

The a-stratified (AS) method enhances Computerized Adaptive Test (CAT) security by controlling item exposure rates. The Maximum Information Stratified (MIS) model further improves accuracy by incorporating the pseudo-guessing parameter (c).

Area of Science:

  • Psychometrics
  • Educational Measurement
  • Computerized Adaptive Testing (CAT)

Background:

  • Increasing security in Computerized Adaptive Tests (CAT) is crucial.
  • The a-stratified (AS) method, proposed by Chang and Ying (1999), stratifies items based on discrimination parameters (a) to manage item exposure rates.
  • The AS method does not utilize the pseudo-guessing parameter (c) from the three-parameter logistic model.

Purpose of the Study:

  • To evaluate the effectiveness of the a-stratified (AS) method in enhancing CAT security.
  • To introduce and assess the Maximum Information Stratified (MIS) model, which incorporates the pseudo-guessing parameter (c).
  • To compare the accuracy and security improvements offered by the MIS model and blocking b methods against the AS method.

Main Methods:

Related Experiment Videos

  • The study analyzes the a-stratified (AS) method, which administers items with increasing discrimination parameters (a) throughout the test.
  • The Maximum Information Stratified (MIS) model is introduced, incorporating the pseudo-guessing parameter (c) into item bank stratification and selection.
  • Blocking b methods are also examined for their impact on item bank security.

Main Results:

  • The AS method leads to a less skewed distribution of item exposure rates while maintaining efficiency in trait-level estimation.
  • The MIS model demonstrates improved accuracy compared to the AS method, irrespective of whether item bank parameters (a and b) are correlated or uncorrelated.
  • Blocking b methods are shown to enhance item bank security for both correlated and uncorrelated parameter banks.

Conclusions:

  • The AS method offers a viable approach to increasing CAT security by managing item exposure.
  • The MIS model provides enhanced accuracy in CAT by integrating the pseudo-guessing parameter (c).
  • Blocking b methods represent a further advancement in securing item banks within CAT environments.