13.1 CDA for Poytomous Response

-Polytomous items are scored with multiple categories and are common in cognitive tests (e.g., essays) and noncognitive tests (e.g., rating scales for personality and attitudes).

-These items typically provide more information than dichotomous items, enabling more accurate parameter estimation.

-Polytomous items avoid respondent frustration and enhance reliability compared to dichotomous rating scales with limited response options.

-They are better suited for assessing higher-level cognitive processes compared to dichotomous items, which often measure lower-level skills.

-Open-ended, polytomously scored items allow direct observation of problem-solving processes, making them ideal for diagnostic purposes.

13.1.1 Few polytomous CDMs

-GDM:General diagnostic model(Davier, 2005)

-PC:DINAthe partial-credit DINA model(De la Torre, 2010)

-P-LCDM: the polytomous LCDM(M. P. Hansen, 2013)

-RSDM:Raticng Scale Diagnostic Model (R. Liu & Jiang, 2020)

-Sequential G-DINA model(Ma et al., 2016)

References

Davier, M. von. (2005). A general diagnostic model applied to language testing data. ETS Research Report Series, 2005(2), i–35.

De la Torre, J. (2010). The partial-credit DINA model. International Meeting of the Psychometric Society.

Hansen, M. P. (2013). Hierarchical item response models for cognitive diagnosis. University of California, Los Angeles.

Liu, R., & Jiang, Z. (2020). A general diagnostic classification model for rating scales. Behavior Research Methods, 52(1), 422–439.

Ma, W., Iaconangelo, C., & Torre, J. de la. (2016). Model similarity, model selection, and attribute classification. Applied Psychological Measurement, 40(3), 200–217.