Overall, the expected advantages of the CAT system are reduced respondent burden, increased score precision, elimination of ceiling and floor effects, patient-specific CIs, monitoring of data quality in real time and lower data collection costs. However, the challenge in developing CAT is the need for large, representative data sets to establish item- and response-characteristic curves, since these tests require "modern" psychometric methods that have only been rarely applied to health questionnaires.
Results
CAT may achieve practical outcome measures. This methodology uses a computerized interview that is tailored to the unique ability level of the individual. The idea behind this is that the adaptive test first asks questions in the middle of the ability range, and then based on the responses, directs questions to the next level without asking unnecessary questions. Also, by making it possible to estimate each person's score, along with a person-specific confidence interval (CI), the number of items administered can be increased, if needed, to achieve the desired level of precision.
blog comments powered by Disqus