Generalizability Theory: A Primer

by Richard J. Shavelson, Noreen M. Webb

In this volume, Shavelson and Webb offer an intuitive development of generalizability theory and cover a wide variety of topics such as generalizability studies with nested facets and with fixed facets, measurement error and generalizability coefficients, and decision studies with same and with different designs. Detailed illustrations, examples and exercises all serve to clearly describe the logic underlying major concepts in generalizability theory and assist readers in applying these methods when investigating the consistency of their own measurements.

152 pages, Hardcover

First published July 23, 1991

Reviews

[Brian · Rating 3 out of 5]

Not a book for everyone. This is a book for which I typically would not write a review, but I think there are some interesting principles of theory here. If you are someone who is going to conduct a study, understand analysis of variance, or someone who just can't stand to see the title of a book without reading it; then this book is for you.

This is actually an easy read for a complex topic. The authors' present the information in a simple and broken down manner with examples that illustrate their points. The diagrams, tables, and practices allow the reader to digest the information presented and test their knowledge. But I would warn that this is a book that may require someone to discuss the concepts with in order to ensure proper understanding.

I would be interested in discussing with someone how the principles of a multi-faceted design, along with the sources of variance and their interactions, may be drawn into a real world scenario. And how might these principles assist us in our daily lives if we were able to apply them to our daily assumptions, reactions, understandings, etc. to the situations before us.

[Alex Rubenstein · Rating 5 out of 5]

Accomplishes everything the authors set out to do, and everything a reader could hope for: an introductory primer that takes one step by step through what G theory is and what it offers beyond CTT, as well as a step by step and easy to follow development of how separate variance components of the measurement process are estimated, and what the researcher or applied practitioner can do to optimize their designs to improve reliability/dependability/generalizability. I think the examples are intuitive and practical, and readers will be able to find clear parallels to the authors examples in how they conduct their own studies.