Tuesday, September 19, 2006

Test fairness - simple definition

I continue to enjoy my current reading of "Knowing what students know"

The book provides many succinct and conrete explanations of various congitive and measurement concepts and, more importantly, is providing me a framework for integrating various developments I've read over the past decade in both cognitive science and measurement.

Today I ran across one nice little example....the books description of "test fairness" (p. 214)
  • "Fairness in testing is defined many ways (see AERA et al., 1999; NRC, 199b), but at its core is the idea of comparable validity: a fair test is one that yields comparably valid inferences from person to person and group to group. An assessment task is considered biased if construct-irrelevant characteristics of the task result in different meanings for different subgroups."


Technorati Tags: , , , , , , , , , , , , ,

powered by performancing firefox

No comments: