Abstract. The Rosenberg Self-Esteem Scale (RSES; Rosenberg, 1965 ) intends to measure a single dominant factor representing global self-esteem. However, several studies have identified some form of multidimensionality for the RSES. Therefore, we examined the factor structure of the RSES with a fixed-effects meta-analytic structural equation modeling approach including 113 independent samples (N = 140,671). A confirmatory bifactor model with specific factors for positively and negatively worded items and a general self-esteem factor fitted best. However, the general factor captured most of the explained common variance in the RSES, whereas the specific factors accounted for less than 15%. The general factor loadings were invariant across samples from the United States and other highly individualistic countries, but lower for less individualistic countries. Thus, although the RSES essentially represents a unidimensional scale, cross-cultural comparisons might not be justified because the cultural background of the respondents affects the interpretation of the items.

Educational large-scale assessments (LSAs) often provide plausible values for the administered competence tests to facilitate the estimation of population effects. This requires the specification of a background model that is appropriate for the specific research question. Because the German National Educational Panel Study (NEPS) is an ongoing longitudinal LSA, the range of potential research questions and, thus, the number of potential background variables for the plausible value estimation grow with each new assessment wave. To facilitate the estimation of plausible values for data users of the NEPS, the R package NEPS scaling allows their estimation following the scaling standards in the NEPS without requiring in-depth psychometric expertise in item response theory. The package only requires the user to prepare the data for the background model. Then, the appropriate item response model including the linking approach adopted for the NEPS is automatically selected, while a nested multiple imputation scheme handles missing values in the background data. For novice users, a graphical interface is provided that does not require knowledge of the R language. Thus, NEPS scaling can be used to estimate cross-sectional and longitudinally linked plausible values for all major competence assessments in the NEPS.

Abstract. Perceptual speed is a basic component of cognitive functioning that allows people to efficiently process novel visual stimuli and quickly react to them. In educational studies, tests measuring perceptual speed are frequently developed using students from regular schools without considering students with special educational needs. Therefore, it is unclear whether these instruments allow valid comparisons between different school tracks. The present study on N = 3,312 students from the National Educational Panel Study evaluated differential item functioning (DIF) of a short test of perceptual speed between four school tracks in Germany (special, basic, intermediate, and upper secondary schools). Bayesian Rasch Poisson counts modeling identified negligible DIF that did not systematically disadvantage specific students. Moreover, the test reliabilities were comparable between school tracks. These results highlight that perceptual speed can be comparably measured in special schools, thus enabling educational researchers to study schooling effects in the German educational system.

Abstract. Response styles (RSs) such as acquiescence represent systematic respondent behaviors in self-report questionnaires beyond the actual item content. They distort trait estimates and contribute to measurement bias in questionnaire-based research. Although various approaches were proposed to correct the influence of RSs, little is known about their relative performance. Because different correction methods formalize the latent traits differently, it is unclear how model choice affects the external validity of the corrected measures. Therefore, the present study on N = 1,000 Dutch respondents investigated the impact of correcting responses to measures of self-esteem and the need for cognition using structural equation models with structured residuals, multidimensional generalized partial credit models, and multinomial processing trees. The study considered three RSs: extreme, midpoint, and acquiescence RS. The results showed homogeneous correlation patterns among the modeled latent and external variables, especially if they were not themselves subject to RSs. In that case, the IRT-based models, including an uncorrected model, still yielded consistent results. Nevertheless, the strength of the effect sizes showed variation.

Item response theory is widely used in a variety of research fields. Among others, it is the de facto standard for test development and calibration in educational large-scale assessments. In this context, longitudinal modeling is of great importance to examine developmental trajectories in competences and identify predictors of academic success. Therefore, this paper describes various multidimensional item response models that can be used in a longitudinal setting and how to estimate change in a Bayesian framework using the statistical software Stan. Moreover, model evaluation techniques such as the widely applicable information criterion and posterior predictive checking with several discrepancy measures suited for Bayesian item response modeling are presented. Finally, an empirical application is described that examines change in mathematical competence between grades 5 and 7 for N = 1, 371 German students using a Bayesian longitudinal item response model.