Description
Test fairness is a moral imperative for both the makers and the users of tests. This book focuses on methods for detecting test items that function differently for different groups of examinees and on using this information to improve tests. Of interest to all testing and measurement specialists, it examines modern techniques used routinely to insure test fairness. Three of these relevant to the book's contents are:
* detailed reviews of test items by subject matter experts and members of the major subgroups in society (gender, ethnic, and linguistic) that will be represented in the examinee population
* comparisons of the predictive validity of the test done separately for each one of the major subgroups of examinees
* extensive statistical analyses of the relative performance of major subgroups of examinees on individual test items.
Reviews
"...this is a fine book. The breadth of coverage will appeal to a wide audience in the testing community, and beyond....It will be the standard reference on DIF for some time."
-Applied Psychological Measurement
Book Information
ISBN 9781138967694
Author Paul W. Holland
Format Paperback
Page Count 470
Imprint Routledge
Publisher Taylor & Francis Ltd
Weight(grams) 635g
