Read more
This authoritative guide directs consumers and users of test scores on when and how to provide subscores and how to make informed decisions based on them. The book is designed to be accessible to practitioners and score users with varying levels of technical expertise, from executives of testing organizations and students who take tests to graduate students in educational measurement, psychometricians, and test developers. The theoretical background required to evaluate subscores and improve them are provided alongside examples of tests with subscores to illustrate their use and misuse. The first chapter covers the history of tests, subtests, scores, and subscores. Later chapters go into subscore reporting, evaluating and improving the quality of subscores, and alternatives to subscores when they are not appropriate. This thorough introduction to the existing research and best practices will be useful to graduate students, researchers, and practitioners.
List of contents
1. Introduction; 2. How are subscores reported?; 3. When and how should subscores be reported?; 4. A survey to explore the conditions under which subscores have added value; 5. What to do when subscores do not have added value. Augmentation, no subscore reporting, and some other options; 6. Coda: Lessons learned, conclusions, and recommendations; Appendix; Glossary; References; Index.
About the author
Shelby Haberman is a statistician with substantial experience in educational testing. He currently works as an independent consultant. Previously he taught at the University of Chicago, Hebrew University, and Northwestern University and was later employed by the Educational Testing Service. He is a fellow of the Institute of Mathematical Statistics, the American Statistical Association, and the American Academy for the Advancement of Science and was the 2019 recipient of the NCME Award for Career Contributions to Educational Measurement. Haberman is the author of 'The Analysis of Frequency Data,' 'Analysis of Qualitative Data,' and 'Advanced Statistics.'Sandip Sinharay is a distinguished presidential appointee in the Research & Development division at the Educational Testing Service in Princeton, New Jersey. He is the current editor of 'Psychometrika,' and a past editor of the 'Journal of Educational Measurement' (2020–2022) and 'Journal of Educational and Behavioral Statistics' (2010–2014). He has received six awards from the National Council on Measurement in Education. He received the ETS Scientist award in 2008 and the ETS Presidential award twice. Sinharay has co-edited two published volumes and authored or co-authored more than 100 articles in peer-reviewed journals and edited books.Richard A. Feinberg has taught at the Graduate School of Education of the University of Pennsylvania and the Philadelphia College of Osteopathic Medicine. He is currently a Principal Psychometrician at the National Board of Medical Examiners where he oversees examination development, scoring, reporting, and operational research for various subspecialty medical boards, the United States Medical Licensing Examination, and the North American Veterinary Licensing Examination. Feinberg has published numerous articles across a broad range of statistical applications in the educational and psychological literature.Howard Wainer is an independent statistician and author with experience in educational testing and data visualization. He has taught at The University of Chicago, Princeton University, and the Wharton School of the University of Pennsylvania. He was employed by the Educational Testing Service from 1980 until 2001 and was the Distinguished Research Scientist at the National Board of Medical Examiners from 2001 until 2016. Wainer is a fellow of the American Statistical Association and American Educational Research Association, and the author or editor of 25 previous books.
