Session S65b (Wednesday, 2pm, Thomas 201)

P821: Using Rasch analysis to evaluate the psychometric properties and performance of assessment instruments

Jack Barbera (University of Northern Colorado, USA)

The validity and reliability of assessment data can be evaluated using variety of theories and models. Item Response Theory (IRT) uses probabilistic models to evaluate an instrument’s items and participants. The Rasch model is an IRT model that uses a single scale to measure a person’s ability and the difficulty of an item. Placing person ability and item difficulty on the same scale allows for direct comparisons of these two variables, a feature not possible with Classical Test Theory. This talk will explore the use of Rasch analysis for gauging the match between the difficulty range of an instrument’s items and the ability range of a target population. The presentation will also include using Rasch analysis to evaluate individual items and their fit to the probabilistic model. The talk will include data generated using a chemistry content assessment.


A sample text widget

Etiam pulvinar consectetur dolor sed malesuada. Ut convallis euismod dolor nec pretium. Nunc ut tristique massa.

Nam sodales mi vitae dolor ullamcorper et vulputate enim accumsan. Morbi orci magna, tincidunt vitae molestie nec, molestie at mi. Nulla nulla lorem, suscipit in posuere in, interdum non magna.