A Strong True-Score Model for Polytomous Items∗
نویسندگان
چکیده
This paper presents a strong true-score model for tests that consist of polytomously-scored items. Errors conditional on true score are assumed to be distributed as multinomial, true category-proportion scores are assumed to follow a Dirichlet distribution, and the marginal category scores are the Dirichletmultinomial distribution. The model is illustrated using real data sets in the following psychometric applications: obtaining a smoothed fitted observed-score distribution; estimating conditional standard errors of measurement and reliability for both raw and transformed scale scores; and computing classification consistency and accuracy indices for raw and scale scores.
منابع مشابه
Examining the Impact of Drifted Polytomous Anchor Items on Test Characteristic Curve (TCC) Linking and IRT True Score Equating
As part of its nonprofit mission, ETS conducts and disseminates the results of research to advance quality and equity in education and assessment for the benefit of ETS's constituents and the field. To obtain a PDF or a print copy of a report, please visit: Abstract In a common-item (anchor) equating design, the common items should be evaluated for item parameter drift. Drifted items are often ...
متن کاملA Multinomial Error Model for Tests with Polytomous Items∗
This paper introduces a multinomial error model, which models the raw scores from polytomously scored items. The multinomial error model is implemented in this paper for estimating conditional standard errors of measurement and reliability for both raw and scale scores. A simulation study is presented, which suggests that the multinomial conditional standard errors of measurement for the raw an...
متن کاملMixed Scoring on Polytomous IRS and the Application in Concepts Diagnosis for Fraction Subtraction
The purpose of this study is to provide the mixed scoring of polytomous item relational structure (PIRS) analysis and utilize it in fraction subtraction concepts diagnosis. There are limitations on dichotomous item relational structure (IRS) and PIRS analysis is well efficient in the analysis of polytomous data. Most utilization of IRS aims to analyze the hierarchical structures of items, not t...
متن کاملDichotomous or polytomous model? equating of testlet-based tests in light of conditional item pair correlations
The performance of dichotomous and polytomous IRT models in equating testletbased tests was compared in this study. To clarify the conditions under which dichotomous and polytomous item response models produce differing results, the DIMTEST program was used for testing essential unidimensionality, and a bias-corrected index (Final Condcorr) was adapted in this study for measuring local item dep...
متن کاملCalibration of Polytomous Item Families Using Bayesian Hierarchical Modeling
For complex educational assessments, there is an increasing use of item families, which are groups of related items. However, calibration or scoring for such an assessment requires fitting models that take into account the dependence structure inherent among the items that belong to the same item family. Glas and van der Linden (2001) suggest a Bayesian hierarchical model to analyze data involv...
متن کامل