IRT model selection methods for dichotomous items

被引:60
|
作者
Kang, Taehoon
Cohen, Allan S.
机构
[1] Univ Wisconsin, Dept Educ Psychol, Madison, WI 53706 USA
[2] Univ Georgia, Athens, GA 30602 USA
关键词
item response theory; model selection; AIC; BIC; DIC; cross-validation log-likelihood; pseudo-Bayes factor; likelihood ratio test;
D O I
10.1177/0146621606292213
中图分类号
O1 [数学]; C [社会科学总论];
学科分类号
03 ; 0303 ; 0701 ; 070101 ;
摘要
Fit of the model to the data is important if the benefits of item response theory (IRT) are to be obtained. In this study, the authors compared model selection results using the likelihood ratio test, two information-based criteria, and two Bayesian methods. An example illustrated the potential for inconsistency in model selection depending on which of the indices was used. Results from a simulation study indicated that the inconsistencies among the indices were common but that model L selection was relatively accurate for longer tests administered to larger sample of examinees. The cross-validation log-likelihood (CVLL) appeared to work the best of the five models for the conditions simulated in this study.
引用
收藏
页码:331 / 358
页数:28
相关论文
共 50 条
  • [31] A Comparison of Estimation Methods for a Multi-unidimensional Graded Response IRT Model
    Kuo, Tzu-Chun
    Sheng, Yanyan
    FRONTIERS IN PSYCHOLOGY, 2016, 7
  • [32] A Comparison of Four Methods of IRT Subscoring
    de la Torre, Jimmy
    Song, Hao
    Hong, Yuan
    APPLIED PSYCHOLOGICAL MEASUREMENT, 2011, 35 (04) : 296 - 316
  • [33] Fourier methods for model selection
    M. D. Jiménez-Gamero
    A. Batsidis
    M. V. Alba-Fernández
    Annals of the Institute of Statistical Mathematics, 2016, 68 : 105 - 133
  • [34] Fourier methods for model selection
    Jimenez-Gamero, M. D.
    Batsidis, A.
    Alba-Fernandez, M. V.
    ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2016, 68 (01) : 105 - 133
  • [35] Bootstrap methods for model selection
    Zoubir, AM
    AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS, 1999, 53 (06) : 386 - 392
  • [36] FUZZY CLASSIFICATION OF DICHOTOMOUS TEST ITEMS AND SOCIAL INDICATORS DIFFERENTIATION PROPERTY
    Krylovas, Aleksandras
    Kosareva, Natalja
    Karaliunaite, Julija
    TECHNOLOGICAL AND ECONOMIC DEVELOPMENT OF ECONOMY, 2018, 24 (04) : 1755 - 1775
  • [37] Selection of unidimensional scales from a multidimensional item bank in the polytomous Mokken IRT model
    Hemker, BT
    Sijtsma, K
    Molenaar, IW
    APPLIED PSYCHOLOGICAL MEASUREMENT, 1995, 19 (04) : 337 - 352
  • [38] A taxonomy of IRT models for ordering persons and items using simple sum scores
    Sijtsma, K
    Hemker, BT
    JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS, 2000, 25 (04) : 391 - 415
  • [39] RESAMPLING METHODS FOR MODEL FITTING AND MODEL SELECTION
    Babu, G. Jogesh
    JOURNAL OF BIOPHARMACEUTICAL STATISTICS, 2011, 21 (06) : 1177 - 1186
  • [40] Detecting DIF in Polytomous Items Using MACS, IRT and Ordinal Logistic Regression
    Elosua, Paula
    Wells, Craig S.
    PSICOLOGICA, 2013, 34 (02): : 327 - 342