Overview
- Features exercises to make the material concrete
- ECD portions of the book (Ch. 2, 12 & 13) build on work that was basis for the 2000 NCME award for Outstanding Technical Contribution to Educational Measurement received by the authors
- Includes basic review of Bayesian probability and statistics and an introduction to Evidence-Centered Design
- Includes supplementary material: sn.pub/extras
Part of the book series: Statistics for Social and Behavioral Sciences (SSBS)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (16 chapters)
-
Back Matter
Keywords
About this book
Bayesian inference networks, a synthesis of statistics and expert systems, have advanced reasoning under uncertainty in medicine, business, and social sciences. This innovative volume is the first comprehensive treatment exploring how they can be applied to design and analyze innovative educational assessments.
Part I develops Bayes nets’ foundations in assessment, statistics, and graph theory, and works through the real-time updating algorithm. Part II addresses parametric forms for use with assessment, model-checking techniques, and estimation with the EM algorithm and Markov chain Monte Carlo (MCMC). A unique feature is the volume’s grounding in Evidence-Centered Design (ECD) framework for assessment design. This “design forward” approach enables designers to take full advantage of Bayes nets’ modularity and ability to model complex evidentiary relationships that arise from performance in interactive, technology-rich assessments such as simulations. Part III describes ECD,situates Bayes nets as an integral component of a principled design process, and illustrates the ideas with an in-depth look at the BioMass project: An interactive, standards-based, web-delivered demonstration assessment of science inquiry in genetics.
This book is both a resource for professionals interested in assessment and advanced students. Its clear exposition, worked-through numerical examples, and demonstrations from real and didactic applications provide invaluable illustrations of how to use Bayes nets in educational assessment. Exercises follow each chapter, and the online companion site provides a glossary, data sets and problem setups, and links to computational resources.
Reviews
“This book will provide valuable information on using data-mining along with graphical models in educational assessment. It is one of the initial works that well explain the operative procedures of designing, validating, and implementing the data-driven, competency-oriented diagnostic assessment. The book should be a good reference for both scholars and practitioners in the areas of educational assessment, learning environments and curriculum design, and school improvement.” (Fengfeng Ke, Technology, Knowledge and Learning, Vol. 24, 2019)
Authors and Affiliations
Bibliographic Information
Book Title: Bayesian Networks in Educational Assessment
Authors: Russell G. Almond, Robert J. Mislevy, Linda S. Steinberg, Duanli Yan, David M. Williamson
Series Title: Statistics for Social and Behavioral Sciences
DOI: https://doi.org/10.1007/978-1-4939-2125-6
Publisher: Springer New York, NY
eBook Packages: Mathematics and Statistics, Mathematics and Statistics (R0)
Copyright Information: Springer Science+Business Media New York 2015
Hardcover ISBN: 978-1-4939-2124-9Published: 11 March 2015
Softcover ISBN: 978-1-4939-3828-5Published: 05 October 2016
eBook ISBN: 978-1-4939-2125-6Published: 10 March 2015
Series ISSN: 2199-7357
Series E-ISSN: 2199-7365
Edition Number: 1
Number of Pages: XXXIII, 662
Number of Illustrations: 68 b/w illustrations, 87 illustrations in colour
Topics: Statistics for Social Sciences, Humanities, Law, Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences, Artificial Intelligence