Rasch Analysis

For EPCC-14, the latent trait was the patient's experience of person-centred care. Rasch analysis was used to assess the test's validity and reliability. The study assessed item and person fit, reliability, differential item functioning, response ordering, targeting, item hierarchy, local dependency, and dimensionality. Reliability was acceptable according to Cronbach's alpha and the Person-Separation Index. Overall Rasch findings supported the iCLAIM Test as a valid and reliable measure of children's ability to assess treatment claims. The person-item distribution indicated acceptable targeting, though the test was somewhat challenging for the cohort. Rasch analysis models item endorsement probability as depending on a person's latent trait level and the item's location or difficulty. The test's underlying measurement assumption was that all items assessed the same ability: applying IHC Key Concepts to treatment claims. Items 4 and 9 underdiscriminated and added little measurement value, while item 21 showed gender-related differential item functioning. Rasch measurement theory was used to test whether the candidate items formed a valid measurement scale. Rasch analysis can test…