Purya Baghaei

This study used explainable Random Forest models to identify predictors of adolescents’ expected active political participation using ICCS 2022 data from 1487 students in Schleswig-Holstein, Germany. Three predictor specifications were examined to distinguish prediction based on variables conceptually close to the outcome from prediction based on more general civic characteristics. The Full Random Forest achieved the highest predictive accuracy (R² = 0.426), with expected legal and electoral participation as the strongest predictors. Removing proximal participation measures reduced predictive accuracy but revealed a stable set of predictors. In the most restrictive model, citizenship self-efficacy, beliefs about missing conventional citizenship, and civic knowledge consistently ranked highest under both permutation importance and SHAP. Civic knowledge showed substantial predictive importance but a consistently negative association with the outcome, supported by the correlation (r = −0.139), SHAP dependence, and ALE analyses. Random Forest’s predictive advantage over benchmark models was modest and specification-dependent.

This study aimed to propose a new method for scoring C-Tests as measures of general language proficiency. In this approach, the unit of analysis is sentences rather than gaps or passages. That is, the gaps correctly reformulated in each sentence were aggregated as sentence score, and then each sentence was entered into the analysis as a polytomous item. Rasch partial credit model was applied to analyze the test. To investigate the effectiveness of the new method, the results of this new strategy were compared with those derived from passage and gap levels as well as combining locally dependent items using the dichotomous Rasch model, the rating scale model, and the partial credit model. The obtained scores from the administration of a C-Test comprising four English passages, each containing 25 gaps, to 160 participants were subjected to dichotomous and polytomous Rasch model analyses. The models were compared regarding individual item fit, person/item separation and reliability, global fit (e.g., deviance), unidimensionality, local item dependence, and person parameters. Results showed the effectiveness of the new scoring method. The suggested strategy increases the number of items compared to the super-item approach, provides information at the sentence level, and reduces the impact of local independence.

C-Test is a gap-filling test designed to measure first and second language proficiency. Over the past four decades, researchers have shown the fit of C-Test data to parametric item response theory (IRT) models, but no study so far has shown the fit of C-Tests to nonparametric IRT models. The purpose of this study is to contribute to the ongoing C-Test validation project by providing evidence of fit to the Mokken scale analysis as a widely used nonparametric IRT model. A six-passage C-Test battery was analyzed using the monotone homogeneity model and the double monotonicity model of Mokken. Unidimensionality was evaluated using the automatic item selection procedure. Findings showed that the C-Test passages form a strong unidimensional scale, fit well to the monotone homogeneity model, and, after deleting one item, have a sufficient fit to the double monotonicity model. The findings also indicated that the items form a hierarchy, and persons can be located on an ordinal scale using their C-Test sum scores. Implications of the study for C-Test validity and application are discussed.

C-tests are gap-filling tests mainly used as rough and economical measures of second-language proficiency for placement and research purposes. A C-test usually consists of several short independent passages where the second half of every other word is deleted. Owing to their interdependent structure, C-test items violate the local independence assumption of IRT models. This poses some problems for IRT analysis of C-tests. A few strategies and psychometric models have been suggested and employed in the literature to circumvent the problem. In this research, a new psychometric model, namely, the loglinear Rasch model, is used for C-tests and the results are compared with the dichotomous Rasch model where local item dependence is ignored. Findings showed that the loglinear Rasch model fits significantly better than the dichotomous Rasch model. Examination of the locally dependent items did not reveal anything as regards their contents. However, it did reveal that 50% of the dependent items were adjacent items. Implications of the study for modeling local dependence in C-tests using different approaches are discussed.

As measures of general language proficiency, C-tests are ubiquitous in language testing. Speeded C-tests are quite recent developments in the field and are deemed to be more discriminatory and provide more accurate diagnostic information than power C-tests especially with high-ability participants. Item response theory modeling of speeded C-tests has not been discussed in the literature, and current approaches for power C-tests based on ordinal models either violate the model assumptions or are relatively complex to be reliably fitted with small samples. Count data models are viable alternatives with less restrictive assumptions and lower complexity. In the current study, we compare count data models with commonly applied ordinal models for modeling a speeded C-test. It was found that a flexible count data model fits equally well in absolute and relative terms as compared with ordinal models. Implications and feasibility of count data models for the psychometric modeling of C-tests are discussed.