View in EDS

Using Deep Reinforcement Learning to Decide Test Length

Saved in:
Bibliographic Details
Title: Using Deep Reinforcement Learning to Decide Test Length
Language: English
Authors: James Zoucha, Igor Himelfarb (ORCID 0000-0002-2622-6062), Nai-En Tang
Source: Educational and Psychological Measurement. 2025 85(5):882-909.
Availability: SAGE Publications. 2455 Teller Road, Thousand Oaks, CA 91320. Tel: 800-818-7243; Tel: 805-499-9774; Fax: 800-583-2665; e-mail: journals@sagepub.com; Web site: https://sagepub.com
Peer Reviewed: Y
Page Count: 28
Publication Date: 2025
Document Type: Journal Articles
Reports - Research
Descriptors: Reinforcement, Test Length, Allied Health Occupations Education, Algorithms, Test Items, Artificial Intelligence
DOI: 10.1177/00131644251332972
ISSN: 0013-1644
1552-3888
Abstract: This study explored the application of deep reinforcement learning (DRL) as an innovative approach to optimize test length. The primary focus was to evaluate whether the current length of the National Board of Chiropractic Examiners Part I Exam is justified. By modeling the problem as a combinatorial optimization task within a Markov Decision Process framework, an algorithm capable of constructing test forms from a finite set of items while adhering to critical structural constraints, such as content representation and item difficulty distribution, was used. The findings reveal that although the DRL algorithm was successful in identifying shorter test forms that maintained comparable ability estimation accuracy, the existing test length of 240 items remains advisable as we found shorter test forms did not maintain structural constraints. Furthermore, the study highlighted the inherent adaptability of DRL to continuously learn about a test-taker's latent abilities and dynamically adjust to their response patterns, making it well-suited for personalized testing environments. This dynamic capability supports real-time decision-making in item selection, improving both efficiency and precision in ability estimation. Future research is encouraged to focus on expanding the item bank and leveraging advanced computational resources to enhance the algorithm's search capacity for shorter, structurally compliant test forms.
Abstractor: As Provided
Entry Date: 20260101
Accession Number: EJ1517593
Database: ERIC
FullText Text:
  Availability: 0
Header DbId: eric
DbLabel: ERIC
An: EJ1517593
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Using Deep Reinforcement Learning to Decide Test Length
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22James+Zoucha%22">James Zoucha</searchLink><br /><searchLink fieldCode="AR" term="%22Igor+Himelfarb%22">Igor Himelfarb</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0002-2622-6062">0000-0002-2622-6062</externalLink>)<br /><searchLink fieldCode="AR" term="%22Nai-En+Tang%22">Nai-En Tang</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Educational+and+Psychological+Measurement%22"><i>Educational and Psychological Measurement</i></searchLink>. 2025 85(5):882-909.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: SAGE Publications. 2455 Teller Road, Thousand Oaks, CA 91320. Tel: 800-818-7243; Tel: 805-499-9774; Fax: 800-583-2665; e-mail: journals@sagepub.com; Web site: https://sagepub.com
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 28
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2025
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Reinforcement%22">Reinforcement</searchLink><br /><searchLink fieldCode="DE" term="%22Test+Length%22">Test Length</searchLink><br /><searchLink fieldCode="DE" term="%22Allied+Health+Occupations+Education%22">Allied Health Occupations Education</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Test+Items%22">Test Items</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink>
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1177/00131644251332972
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 0013-1644<br />1552-3888
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This study explored the application of deep reinforcement learning (DRL) as an innovative approach to optimize test length. The primary focus was to evaluate whether the current length of the National Board of Chiropractic Examiners Part I Exam is justified. By modeling the problem as a combinatorial optimization task within a Markov Decision Process framework, an algorithm capable of constructing test forms from a finite set of items while adhering to critical structural constraints, such as content representation and item difficulty distribution, was used. The findings reveal that although the DRL algorithm was successful in identifying shorter test forms that maintained comparable ability estimation accuracy, the existing test length of 240 items remains advisable as we found shorter test forms did not maintain structural constraints. Furthermore, the study highlighted the inherent adaptability of DRL to continuously learn about a test-taker's latent abilities and dynamically adjust to their response patterns, making it well-suited for personalized testing environments. This dynamic capability supports real-time decision-making in item selection, improving both efficiency and precision in ability estimation. Future research is encouraged to focus on expanding the item bank and leveraging advanced computational resources to enhance the algorithm's search capacity for shorter, structurally compliant test forms.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 20260101
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1517593
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1517593
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1177/00131644251332972
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 28
        StartPage: 882
    Subjects:
      – SubjectFull: Reinforcement
        Type: general
      – SubjectFull: Test Length
        Type: general
      – SubjectFull: Allied Health Occupations Education
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Test Items
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
    Titles:
      – TitleFull: Using Deep Reinforcement Learning to Decide Test Length
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: James Zoucha
      – PersonEntity:
          Name:
            NameFull: Igor Himelfarb
      – PersonEntity:
          Name:
            NameFull: Nai-En Tang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 0013-1644
            – Type: issn-electronic
              Value: 1552-3888
          Numbering:
            – Type: volume
              Value: 85
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Educational and Psychological Measurement
              Type: main
ResultId 1