×

A class of multidimensional latent class IRT models for ordinal polytomous item responses. (English) Zbl 1462.62400

Summary: We propose a class of multidimensional Item Response Theory models for polytomously-scored items with ordinal response categories. This class extends an existing class of multidimensional models for dichotomously-scored items in which the latent abilities are represented by a random vector assumed to have a discrete distribution, with support points corresponding to different latent classes in the population. In the proposed approach, we allow for different parameterizations for the conditional distribution of the response variables given the latent traits, which depend on the type of link function and the constraints imposed on the item parameters. Moreover, we suggest a strategy for model selection that is based on a series of steps consisting of selecting specific features, such as the dimension of the model (number of latent traits), the number of latent classes, and the specific parameterization. In order to illustrate the proposed approach, we analyze a dataset from a study on anxiety and depression on a sample of oncological patients.

MSC:

62H99 Multivariate analysis
62P15 Applications of statistics to psychology

Software:

MultiLCIRT
PDF BibTeX XML Cite
Full Text: DOI arXiv Link

References:

[1] DOI: 10.1177/0146621697211001
[2] Agresti A., Scand. J. Statist. 20 pp 63– (1993)
[3] DOI: 10.1002/0471249688
[4] Akaike H., Proceeding of the Second International Symposium on Information Theory pp 267– (1973)
[5] DOI: 10.1007/BF02293814 · Zbl 0438.62086
[6] DOI: 10.1007/s11336-005-1376-9 · Zbl 1286.62099
[7] DOI: 10.1016/j.csda.2013.05.018 · Zbl 1471.62024
[8] Birnbaum A., Statistical Theories of Mental Test Scores pp 395– (1968)
[9] DOI: 10.1007/BF02295131 · Zbl 1297.62228
[10] Dempster A. P., J. Roy. Statist. Soc. Ser. B 39 pp 1– (1977)
[11] DOI: 10.1016/0049-089X(87)90003-2
[12] DOI: 10.1080/01621459.1992.10475229
[13] DOI: 10.1093/biomet/61.2.215 · Zbl 0281.62057
[14] Haberman S. J., Tech. Rep., ETS Research Rep. No. RR-08-45 (2008)
[15] DOI: 10.1007/978-94-017-1988-9
[16] Heinen T., Latent Class and Discrete Latent Traits Models: Similarities and Differences. Advanced Quantitative Techniques in the Social Sciences 6 (1996)
[17] DOI: 10.1007/BF02295273 · Zbl 1003.62548
[18] DOI: 10.1177/014662169602000205
[19] DOI: 10.1007/BF02295181 · Zbl 0825.62936
[20] DOI: 10.1007/978-1-4757-5644-9
[21] Lazarsfeld P. F., Latent Structure Analysis (1968) · Zbl 0182.52201
[22] DOI: 10.1080/01621459.1991.10475008
[23] Martin-Löf P., Statistiska Modeller (1973)
[24] DOI: 10.1007/BF02296272 · Zbl 0493.62094
[25] DOI: 10.1007/BF02294149
[26] DOI: 10.1177/014662169401800305
[27] Molenaar I. W., Item Steps (Heymans Bullettin 83-630-(OX) (1983)
[28] DOI: 10.1177/014662169001400106
[29] DOI: 10.1177/014662169201600206
[30] DOI: 10.1007/978-1-4757-2691-6_9
[31] Nering M. L., Handbook of Polytomous Item Response Theory Models (2010)
[32] Rasch G., Probabilistic Models for Some Intelligence and Attainment Tests (1960)
[33] DOI: 10.1007/978-0-387-89976-3 · Zbl 1291.62023
[34] DOI: 10.1111/j.2044-8317.1991.tb00951.x
[35] Samejima F., Psychometrika Monograph 17 (1969)
[36] DOI: 10.1007/BF02294328 · Zbl 0862.62088
[37] DOI: 10.2333/bhmk.23.17 · Zbl 04530310
[38] DOI: 10.1214/aos/1176344136 · Zbl 0379.62005
[39] Smit A., Meth. Psychol. Res. Online 8 pp 23– (2003)
[40] DOI: 10.1111/j.2044-8317.1990.tb00925.x · Zbl 0718.62263
[41] DOI: 10.1177/01466210122032073
[42] DOI: 10.1007/978-1-4757-2691-6
[43] DOI: 10.1177/01466210122032082
[44] DOI: 10.1348/000711007X193957
[45] von Davier M., Rasch Models. Foundations, Recent Developments, and Applications pp 371– (1995)
[46] Zhang J., Tech. Rep., ETS Research Rep. No. RR-04-44 (2004)
[47] DOI: 10.1111/j.1600-0447.1983.tb09716.x
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.