Research is needed on the myths regarding child sexual abuse in order to address commonly held misconceptions persons training for professional careers relevant fields protection. We present our translated, validated, and expanded Child Sexual Abuse Myth Scale (CSAMS-G). It was tested a sample of 569 students studying either education, social work, law, or policing. Results confirmatory factor analysis revealed good model fit assumed factorial structure. Acceptable results internal...

We conducted two studies on using random forest (RF) analysis with explainable artificial intelligence (XAI) to detect differential item functioning (DIF) in multidimensional response theory (MIRT) models. RF-XAI identifies DIF-items by their importance predicting group membership from responses and person parameters. Study 1 examines how test characteristics, namely DIF-item proportion, sample size, dimensionality, the RF parameter mtry affect variable detection metrics. High rates low...

Abstract Social approaches can contribute to clarifying environmental issues. For instance, social identity theory help comprehend people's motivations for getting involved in protection. However, the kind of best suited predicting protection engagement remains unclear. This study examines different categories relation types engagement. The predictive power identification with environmentalists, as well politicized and non‐politicized groups, are considered separately. Furthermore, is...

This study presents a novel method to investigate test fairness and differential item functioning combining psychometrics machine learning. Test unfairness manifests itself in systematic demographically imbalanced influences of confounding constructs on residual variances psychometric modeling. Our aims account for resulting complex relationships between response patterns demographic attributes. Specifically, it measures the importance individual items, latent ability scores comparison...

Zusammenfassung: Die psychologische Einzelfalldiagnostik erfordert oft konkrete Entscheidungen, z. B. ob Personen in einem psychologischen Bereich „unterdurchschnittlich“ sind. Alle deutschen Lehrbücher empfehlen, die Messunsicherheit von Tests zu berücksichtigen, durch kritische Differenzen, Hypothesentests oder Konfidenzintervalle. Diese Empfehlungen ähneln jedoch Heuristiken ohne eine nachvollziehbare Begründung, wie das geeignete Signifikanz- Konfidenzniveau wählen ist. statistische...

This contribution presents TreaDeF, a fully formalized and uncertainty aware diagnostic treatment decision framework. TreaDeF is situated within statistical theory, merging traditional informal, human-centered, making, algorithmic making. extends existing approaches, combining traditions of psychometrics econometrics by incorporating measurement uncertainty. Treatment options represent actions. Personal characteristics, determining success, states. The framework the classical theoretic setup...

The coronavirus-related school closures in Bavaria, as Germany a whole, lasted from March to June 2020 and were therefore on an average scale internationally. This study investigates the impact of these reading fluency elementary students. To evaluate short-term one month) long-term (one year) effects third-grade fluency, we use longitudinal causal approach. involved 9,083 students Bavaria,divided into two cohorts: affected by closures, control cohort who experienced second grade year...

Abstract: In this study, we compared three different models of reading comprehension on a large dataset more than 6,500 students. We two representing four processes as well the influence text difficulty to one-factor model by applying multi-dimensional item response newly developed Bavarian test (BYLET). Cross-validation indicated best generalizability for model, but factor loadings and global fit showed some evidence measured word sentence length process structure. All psychometric tested...

In this study, we compared different models of reading comprehension on a large data basis more than 6500 students. We examine representing the Simple View Reading, four-process-model as well influence text difficulty by applying psychometric modeling in framework item response theory to newly developed Bavarian test BYLET. Results demonstrate best fit for four-process model and negligible measured word sentence length. The were robust indicated cross-validation showed good reliability...

Classical statistical methods are limited in the analysis of highdimensional datasets. Machine learning (ML) provides a powerful framework for prediction by using complex relationships, often encountered modern data with large number variables, cases and potentially non-linear effects. ML has turned into one most influential analytical approaches this millennium recently become popular behavioral social sciences. The impact on research practical applications educational sciences is still...

There is a large number of scientifically evaluated reading trainings recommended by literature, that have shown to be effective on the process level. However, field studies indicate teachers rarely adopt those but use animation methods and self-invented instead. Yet, scientific evidence for teacher-constructed still missing. We therefore asked 87 about their lessons assessed ability development 1469 students with standardized test. The results show hardly any evidence-based methods, mainly...

The present investigation comprises two studies. In Study 1, participants gave numerical information about demographic attributes (real-scores). They subsequently rated themselves regarding these on a five-point Likert-type scale (5LTS). Items used different phrasings, inducing (1) general, (2) personal, and (3) an outsiders’ perspective. By regressing ratings the real-scores, it was shown that centers intervals of real-scores were not readily reflected by response scales. This led to...

This study presents a novel method to investigate test fairness combining psychometrics and machine learning. Test unfairness manifests itself in systematic demographically imbalanced influences of confounding constructs on residual variances psychometric modelling. Our disentangles the underlying complex relationships between response patterns demographic attributes. Specifically, it measures importance individual items latent ability scores predicting characteristics as indicators...

__Abstract__: Psychological assessment often requires concrete decisions, e.g. whether a person is “below the norm” in some psychological domain. It still common that practitioners directly compare test score with theoretical norm value (e.g., one standard deviation below mean). In literature review, we show all German textbooks on Assessment recommend taking measurement uncertainty of tests into account, for example by using critical differences, hypothesis tests, or confidence intervals....

Classical statistical methods are limited in the analysis of highdimensional datasets. Machine learning (ML) provides a powerful framework for prediction by using complex relationships, often encountered modern data with large number variables, cases and potentially non-linear effects. ML has turned into one most influential analytical approaches this millennium recently become popular behavioral social sciences. The impact on research practical applications educational sciences is still...