|
Abstract:
|
The federal legislation, No Child Left Behind, requires states to test students each year, rate schools on the basis of student performance, and intervene in schools that do not make adequate annual improvement. A shortcoming of such scheme, however, is that it is likely to induce behavior distortions such as student/teacher seeking to cheat in the test. Researchers proposed different approaches to detect such behavior. We would like to discuss different cheating detection methods and compare their performance through real and simulated data. Based on our current survey, these approaches include (but not limit to) excessive similarity detection using multiple choice items, regression based technique using multiple choice and constructed response items, longitudinal track of class or school level performance.
|
