Abstract
A method is presented for analyzing the response data from student evaluations of teaching. The method is an objective one, based on inferential statistical techniques which assume only the known structure of the response data and are sensitive to the numbers of respondents involved. Provision is made for comparing instructors of similar classes, but the comparative information supplied pertains to specific aspects of teaching performance rather than overall rankings. The method is conservative yet sufficiently discriminatory, detecting both deficient and outstanding teaching. Consequently, the method can provide the reliable information necessary if evaluations by students are to be effective in promoting good instruction.
Get full access to this article
View all access options for this article.