Developing an Item Bank of Computerized Adaptive Testing for Eating Disorders in Chinese University Students

Abstract

We aimed to develop an item bank of computerized adaptive testing for eating disorders (CAT-ED) in Chinese university students to increase measurement precision and improve test efficiency. A total of 1,025 Chinese undergraduate respondents answered a series of questions about eating disorders in a paper-pencil test. A total of 133 items from four well-validated Chinese-version scales of eating disorders were used to construct the item bank of CAT-ED with the following analysis. First, unidimensionality, model fit, local independence, item fit, discrimination and differential item functioning (DIF) were tested. Then, two simulation studies were applied to test the CAT-ED’s effectivity and rationality by calculating concurrent criterion-related validity, sensitivity and specificity. The final item bank comprised 77 items, which met the requirements of local independence, item fit, high discrimination and no differential item functioning in CAT. The mean number of administered items in CAT with the stopping rule fixed at SE ≤ 0.3 was 11 items. The obtained results showed that CAT-ED had acceptable reliability, validity, sensitivity and specificity.

Application of the professional maturity scale as a computerized adaptive testing

“…The study also found that when variable length stopping rules are used (SE<0.30; SE<0.50; SE<0.70), ability estimation can be made with 84%-90% fewer items than the original scale. This finding is in parallel with the advantage of the following ratios in the number of items: the rate of 73.3% was reached as a result of the study of Gardner et al (2004); the rates of 36%-65% reached as a result of the study of Smits et al (2011); the 50.86% rate reached as a result of Aybek and Demirtaşlı's ( 2017) study; the rate of 75% obtained in the study of Gibbons et al (2016); the rate of 67% obtained in the study by Stochl et al (2016); the 50%-85% rates obtained in the study by Petersen et al (2016); the 30%-71% rates obtained in the study by Choi and McClenen (2020); the rate of 75% obtained in the study by Harrison et al (2020); the 50%-63% rates obtained in the study by Yasuda et al (2021); the 62%-96% rates obtained in the study by Liu et al (2022); the rate of 78% obtained in the study by Giordano et al (2023). In the studies conducted by Smits et al (2011) andAybek andDemirtaşlı (2018), it can be said that the low ratio in test lengths is because there is a more limited pool of items compared to other studies.…”

Exercise Generation and Student Cognitive Ability Research Based on ChatGPT and Rasch Model

“…The effectiveness and rationality of CAT-ED were examined by calculating validity, sensitivity, and specificity correlations with standards. The final item bank comprised 77 items that met the testing requirements [10].The advent of computer-adaptive testing has improved the accuracy and relevance of exercise design. However, there is still room for improvement in terms of design efficiency, and further research is needed to refine the parameters used in these enhancements.…”