A Shadow-Test Approach to Adaptive Item Calibration

Wim J. van der Linden; Bingnan Jiang

doi:10.1007/s11336-020-09703-8

A Shadow-Test Approach to Adaptive Item Calibration

Wim J. van der Linden^*, Bingnan Jiang

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

6 Citations (Scopus)

131 Downloads (Pure)

Abstract

A shadow-test approach to the calibration of field-test items embedded in adaptive testing is presented. The objective function used in the shadow-test model selects both the operational and field-test items adaptively using a Bayesian version of the criterion of D_s-optimality. The constraint set for the model can be used to hide the field-test items completely in the content of the test as well as to deal with such practical issues as random control of their exposure rates. The approach runs on efficient implementations of the Gibbs sampler for the real-time updating of the ability and field-test parameters. Optimal settings for the proposed algorithms were found and used to demonstrate item calibration with smaller than traditional sample sizes in runtimes fully comparable with conventional adaptive testing.

Original language	English
Pages (from-to)	301-321
Number of pages	21
Journal	Psychometrika
Volume	85
Issue number	2
DOIs	https://doi.org/10.1007/s11336-020-09703-8
Publication status	Published - 17 Jun 2020

Keywords

UT-Hybrid-D
Bayesian D-optimality
Gibbs sampling
Item calibration
Item response models
MCMC algorithm
Shadow-test approach
Adaptive testing

Access to Document

10.1007/s11336-020-09703-8Licence: CC BY

ArticleFinal published version, 2.25 MBLicence: CC BY

Cite this

@article{1f15139322364a96b59af23063a80d74,

title = "A Shadow-Test Approach to Adaptive Item Calibration",

abstract = "A shadow-test approach to the calibration of field-test items embedded in adaptive testing is presented. The objective function used in the shadow-test model selects both the operational and field-test items adaptively using a Bayesian version of the criterion of Ds-optimality. The constraint set for the model can be used to hide the field-test items completely in the content of the test as well as to deal with such practical issues as random control of their exposure rates. The approach runs on efficient implementations of the Gibbs sampler for the real-time updating of the ability and field-test parameters. Optimal settings for the proposed algorithms were found and used to demonstrate item calibration with smaller than traditional sample sizes in runtimes fully comparable with conventional adaptive testing.",

keywords = "UT-Hybrid-D, Bayesian D-optimality, Gibbs sampling, Item calibration, Item response models, MCMC algorithm, Shadow-test approach, Adaptive testing",

author = "{van der Linden}, {Wim J.} and Bingnan Jiang",

note = "Springer deal",

year = "2020",

month = jun,

day = "17",

doi = "10.1007/s11336-020-09703-8",

language = "English",

volume = "85",

pages = "301--321",

journal = "Psychometrika",

issn = "0033-3123",

publisher = "Cambridge University Press",

number = "2",

}

TY - JOUR

T1 - A Shadow-Test Approach to Adaptive Item Calibration

AU - van der Linden, Wim J.

AU - Jiang, Bingnan

N1 - Springer deal

PY - 2020/6/17

Y1 - 2020/6/17

N2 - A shadow-test approach to the calibration of field-test items embedded in adaptive testing is presented. The objective function used in the shadow-test model selects both the operational and field-test items adaptively using a Bayesian version of the criterion of Ds-optimality. The constraint set for the model can be used to hide the field-test items completely in the content of the test as well as to deal with such practical issues as random control of their exposure rates. The approach runs on efficient implementations of the Gibbs sampler for the real-time updating of the ability and field-test parameters. Optimal settings for the proposed algorithms were found and used to demonstrate item calibration with smaller than traditional sample sizes in runtimes fully comparable with conventional adaptive testing.

AB - A shadow-test approach to the calibration of field-test items embedded in adaptive testing is presented. The objective function used in the shadow-test model selects both the operational and field-test items adaptively using a Bayesian version of the criterion of Ds-optimality. The constraint set for the model can be used to hide the field-test items completely in the content of the test as well as to deal with such practical issues as random control of their exposure rates. The approach runs on efficient implementations of the Gibbs sampler for the real-time updating of the ability and field-test parameters. Optimal settings for the proposed algorithms were found and used to demonstrate item calibration with smaller than traditional sample sizes in runtimes fully comparable with conventional adaptive testing.

KW - UT-Hybrid-D

KW - Bayesian D-optimality

KW - Gibbs sampling

KW - Item calibration

KW - Item response models

KW - MCMC algorithm

KW - Shadow-test approach

KW - Adaptive testing

UR - http://www.scopus.com/inward/record.url?scp=85086742805&partnerID=8YFLogxK

U2 - 10.1007/s11336-020-09703-8

DO - 10.1007/s11336-020-09703-8

M3 - Article

AN - SCOPUS:85086742805

SN - 0033-3123

VL - 85

SP - 301

EP - 321

JO - Psychometrika

JF - Psychometrika

IS - 2

ER -

A Shadow-Test Approach to Adaptive Item Calibration

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this