Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Unit
Browse By Session Type
Search Tips
What to do in Chicago
Personal Schedule
Sign In
X (Twitter)
Tests are typically designed to measure a particular latent trait. The word measure implies providing an interval or ratio scale framework to describe the amount of the latent trait held by the object of measurement. Many tests do successfully create an interval scale metric; however, there is often a disconnect between the indicator of the amount (score) and what it implies about the examinee. This paper describes a method to connect scores with their substantive meaning by condensing the essence of exam questions and organizing them into a hierarchy using their difficulty calibrations. The end product is a “ruler” that visually illustrates the construct of an exam.
Michael Peabody, American Board of Family Medicine
Thomas R. O'Neill, American Board of Family Medicine
Roger Fain, American Board of Family Medicine
Lars Peterson, American Board of Family Medicine
Melanie Lybarger, American Board of Family Medicine