Date | Speaker & Title | Description |
December 6, 2021 |
The 1st keynote speech: 8:30am-9:20am (40-min presentation and 10-min Q & A) | Prof. Ricardo PRIMI BRAZIL Response styles as Person Differential Functioning: methodological approaches to solve Person DIF | Likert-type self-report scales are frequently used in large-scale educational assessment of social-emotional skills. Self-report scales rely on the assumption that their items elicit information only about the trait they are supposed to measure. Specifically, in children, the response style of acquiescence is an important source of systematic error. Balanced scales, including an equal number of positively and negatively keyed items, have been proposed as a solution to control for acquiescence, but the reasons why this design feature worked from the perspective of modern psychometric models have been underexplored. Three methods for controlling for acquiescence are compared: classical method by partialling out the mean; an item response theory method to measure differential person functioning (DPF); and multidimensional item response theory (MIRT) with random intercept. Comparative analyses are conducted on simulated ratings and on self-ratings provided by 40,649 students (aged 11–18) on a fully balanced 30-item scale assessing conscientious self-management. Acquiescence bias was found to be explained as DPF. |
Break: 9:20am-9:30am (10 mins) |
The 2nd keynote speech: 9:30am – 10:20am (40-min presentation and 10-min Q & A) | Prof. Kelly BRADLEY AMERICA (Soon) | (Soon) |
Break: 10:20am-10:40am (20 mins) |
The 3rd keynote speech: 10:40am – 11:30am (40-min presentation and 10-min Q & A) | Prof. Steven STEMLER AMERICA Better Measurement and Fewer Parameters! The True Value of Rasch over IRT | Proponents of Item Response Theory models have sometimes described the Rasch model as “the one-parameter IRT model”. In doing so, however, they miss both the point and the power of Rasch model. Only the Rasch model can guarantee that the scale being constructed has the same meaning for all test takers, and this provides a powerful advantage over 2 and 3 parameter IRT models. By modeling a second parameter (item discrimination) and allowing item characteristic curves to cross, as IRT models do, more information is incorporated into person ability and item difficulty estimates, but this comes with an attendant loss in the power to interpret the test scale in a way that means the same thing for all test takers. Thus, any approach to assessment that aims to be able to report what all test-takers know and can do at each level of ability or which hopes to use adaptive testing algorithms to select the appropriate items to administer must necessarily rely on the Rasch model and not on 2 or 3 parameter IRT models. |