Reasoning is regarded to be an essential facet of fundamental cognitive abilities. As examinee characteristics may affect performance in Reasoning tests, concern about maintaining fairness is expressed. The purpose of the current study was to examine effects of response format on psychometric properties and fairness of a matrices test according to examinee's sex, risk propensity, and test anxiety. A total of 433 German-speaking pupils (aged 14-20) were randomly assigned to either a multiple choice or a free response version of the same 25-item test. Data analysis yielded Rasch-homogeneous 23-item versions, with higher reliability, but lower criterion validity for the free response test. No interactions between response format and sex, test anxiety, or risk propensity were revealed, but a significant main effect of sex: men out-performed women in reasoning irrespective of response format. Results are discussed with reference to attributes of the test situation and sample characteristics.

No abstract

Abstract. Reasoning ability has commonly been regarded as the best predictor of academic and occupational success. Due to concerns about the validity of multiple-choice (MC) formats, test security breaches, and the fact that the difficulty levels of most existing reasoning assessments target the population mean, there is a constant need for new reliable and valid test instruments that can be applied to assess fluid intelligence in advanced cognitive performance areas. We developed a novel computerized figural matrices test to assess nonverbal reasoning for university student aptitude assessment. In two studies, we generated, revised, and empirically validated the Isometric Matrices Test (IMT). Our results show that the IMT is less prone to test-wiseness strategies than existing reasoning tests. In a third study, we created and evaluated an innovative Find the Mistake (FtM) response format as an alternative to classical multiple-choice formats. Overall, both response formats revealed satisfactory psychometric quality in terms of item difficulties and discrimination, test-retest reliability, construct and criterion validity, and Rasch or two-parameter logistic (2PL) model fit, but in one MC version, the internal consistency was low due to negative discrimination indices. The MC response format turned out to be easier than the FtM format, with men slightly outperforming women in both response modes. We propose the IMT as a useful tool for assessing nonverbal reasoning ability in above-average performance areas and discuss the automatic generation of larger IMT item pools for adaptive testing in order to increase test security and reliability.

Psychological achievement and aptitude tests are fundamental elements of the everyday school, academic and professional lives of students, instructors, job applicants, researchers and policymakers. In line with growing demands for fair psychological assessment tools, we aimed to identify psychometric features of tests, test situations and test-taker characteristics that may contribute to the emergence of test bias. Multi-level random effects meta-analyses were conducted to estimate mean effect sizes for differences and relations between scores from achievement or aptitude measures with open-ended (OE) versus closed-ended (CE) response formats. Results from 102 primary studies with 392 effect sizes revealed positive relations between CE and OE assessments (mean r = 0.67, 95% CI [0.57; 0.76]), with negative pooled effect sizes for the difference between the two response formats (mean d av = −0.65; 95% CI [−0.78; −0.53]). Significantly higher scores were obtained on CE exams. Stem-equivalency of items, low-stakes test situations, written short answer OE question types, studies conducted outside the United States and before the year 2000, and test-takers' achievement motivation and sex were at least partially associated with smaller differences and/or larger relations between scores from OE and CE formats. Limitations and the results’ implications for practitioners in achievement and aptitude testing are discussed.