Applied Multivariate Statistics for the Social Sciences

Stevens, James P.

ISBN 10: 0805811974 ISBN 13: 9780805811971

Publisher: Lawrence Erlbaum Associates Inc, 1992

Synopsis

This best-selling text is written for those who use, rather than develop statistical methods. Dr. Stevens focuses on a conceptual understanding of the material rather than on proving results. Helpful narrative and numerous examples enhance understanding and a chapter on matrix algebra serves as a review. Annotated printouts from SPSS and SAS indicate what the numbers mean and encourage interpretation of the results. In addition to demonstrating how to use these packages, the author stresses the importance of checking the data, assessing the assumptions, and ensuring adequate sample size by providing guidelines so that the results can be generalized. The book is noted for its extensive applied coverage of MANOVA, its emphasis on statistical power, and numerous exercises including answers to half.

The new edition features:

• New chapters on Hierarchical Linear Modeling (Ch. 15) and Structural Equation Modeling (Ch. 16)
• New exercises that feature recent journal articles to demonstrate the actual use of multiple regression (Ch. 3), MANOVA (Ch. 5), and repeated measures (Ch. 13)
• A new appendix on the analysis of correlated observations (Ch. 6)
• Expanded discussions on obtaining non-orthogonal contrasts in repeated measures designs with SPSS and how to make the identification of cell ID easier in log linear analysis in 4 or 5 way designs
• Updated versions of SPSS (15.0) and SAS (8.0) are used throughout the text and introduced in chapter 1
• A book website with data sets and more.

Ideal for courses on multivariate statistics found in psychology, education, sociology, and business departments, the book also appeals to practicing researchers with little or no training in multivariate methods. Prerequisites include a course on factorial ANOVA and covariance. Working knowledge of matrix algebra is not assumed.

About this title

Review

"In summary, this book will appeal to graduate students in a variety of disciplines including psychology, education, business, and management. It is an excellent text that could be used in courses on multivariate analysis that are targeted toward students who probably do not have a Master's degree in mathematics or statistics...Topics are explained clearly and the examples and explanations of results make the techniques described therein understandable. I particularly appreciated the emphasis on power, evaluation of assumptions, cross-validation, and concerns about capitalization on chance."
—Organizational Research Methods

"The book is sprinkled with practical advice that researchers will find useful when applying these techniques to their work....Beginning users of multivariate statistics will appreciate the detailed examples from the social-science literature that include annotated output....Stevens does an excellent job of conveying how multivariate statistics is currently performed in the social sciences, with advice along the way on how to improve the status quo."
—The American Statistician

"...Dr. Stevens writes so clearly. My students tell me in unsolicited comments that his text is helpful in developing their understanding. The material is presented in an informative and engaging manner."
—Gary J. Lautenschlager
University of Georgia

"The liberal inclusion of data examples using such packages as SAS and SPSS is especially helpful to the students."
—Daniel D. Blaine
University of Hawaii at Manoa

About the Author

University of Cincinnati

Edition details

• Publisher: Lawrence Erlbaum Associates Inc
• Publication date: 1992
• Language: English
• ISBN 10: 0805811974
• ISBN 13: 9780805811971
• Binding: Loose Leaf
• Edition number: 2
• Number of pages: 648