Reading and Understanding More Multivariate Statistics

Since 1995, over 13,000 graduate students and researchers have relied on Reading and Understanding Multivariate Statistics for a basic understanding of the most commonly used multivariate analyses in the research literature today. In Reading and Understanding MORE Multivariate Statistics, the editors have responded to reader requests to provide the same accessible approach to a new group of multivariate techniques and related topics in measurement. Chapters demystify the use of cluster analysis, Q-technique factor analysis, structural equation modeling, canonical correlation analysis, repeated measures analyses, and survival analysis. As with the previous volume, chapter authors describe the research questions for which the statistic is most appropriate, the underlying assumptions and rationale of the analysis, and the logic behind interpreting the results. Designed to clarify each statistic's logic and utility rather than teach hands-on application, the book emphasizes the real-world use of statistical methods with minimal reliance on complex mathematical formulas. Each chapter contains accessible discussions of general principles, instructions for interpreting summary tables, and a glossary of key terms and statistical notations. Whether you are a graduate student, researcher, or consumer of research, this volume is guaranteed to increase your comfort level and confidence in reading and understanding multivariate statistics. In Reading And Understanding More Multivariate Statistics, Laurence G. Grimm And Paul R. Yarnold Have Responded To Reader Requests To Provide The Same Accessible Approach To A New Group Of Multivariate Techniques And To Related Topics In Measurement. Chapters Demystify The Use Of Cluster Analysis, Q-technique Factor Analysis, Structural Equation Modeling, Canonical Correlation Analysis, Repeated Measures Analysis, And Survival Analysis. As With The Previous Volume, Chapter Authors Describe The Research Questions For Which The Analysis Is Most Appropriate, The Underlying Assumptions And Rationale Of The Analysis, And The Logic Behind Interpreting The Results. Whether You Are A Graduate Student, Researcher, Or Consumer Of Research, This Volume Is Guaranteed To Increase Your Comfort Level And Confidence In Reading And Understanding Multivariate Statistics.--jacket. Introduction To Multivariate Statistics / Laurence G. Grimm And Paul R. Yarnold -- Reliability And Generalizability Theory / Michael J. Strube -- Item Response Theory / David H. Henard -- Assessing The Validity Of Measurement / Fred B. Bryant -- Cluster Analysis / Joseph F. Hair, Jr., And William C. Black -- Q-technique Factor Analysis : One Variation On The Two-mode Factor Analysis Of Variables / Bruce Thompson. Structural Equation Modeling / Laura Klem -- Ten Commandments Of Structural Equation Modeling / Bruce Thompson -- Canonical Correlation Analysis / Bruce Thompson -- Repeated Measures Analyses : Anova, Manova, And Hlm / Kevin P. Weinfurt -- Survival Analysis / Raymond E. Wright. Edited By Laurence G. Grimm And Paul R. Yarnold. Includes Bibliographical References And Index. "This book is written for an audience with no formal exposure to multivariate statistics; a grasp of univariate statistics is essential, however. Concepts and symbols are presented with minimal reliance on formulas. The authors provide example applications of each statistical analysis, the underlying assumptions and mechanics of the analysis, and a discussion of an interesting working example. The reader should be able to achieve an understanding of many multivariate procedures and approaches to measurement, without getting lost in the minutia of mathematical formulas and derivations that are not presented. Each chapter includes a glossary of terms and symbols that provides a quick way to access succinct definitions of fundamental concepts discussed in the text. The authors present fundamental conceptual aspects of multivariate techniques and measurement topics, and explain these procedures in simple, intuitive terms, using as few equations as possible. For graduate students, this book may be a useful companion to the many standard texts that teach the students to perform multivariate analyses in statistics courses as preparation for doing their own research"--Introduction. (PsycINFO Database Record (c) 2015 APA, all rights reserved) "In Reading and Understanding MORE Multivariate Statistics, Laurence G. Grimm and Paul R. Yarnold have responded to reader requests to provide the same accessible approach to a new group of multivariate techniques and to related topics in measurement. Chapters demystify the use of cluster analysis, Q-technique factor analysis, structural equation modeling, canonical correlation analysis, repeated measures analysis, and survival analysis. As with the previous volume, chapter authors describe the research questions for which the analysis is most appropriate, the underlying assumptions and rationale of the analysis, and the logic behind interpreting the results. Whether you are a graduate student, researcher, or consumer of research, this volume is guaranteed to increase your comfort level and confidence in reading and understanding multivariate statistics."--BOOK JACKET. This follow up text to the editors' Reading and Understanding Multivariate Statistics applies the accessible approach of the previous work to a new group of multivariate techniques and to related topics in measurement. The text seeks to demystify the use of cluster analysis, Q-technique factor analysis, structural equation modeling, canonical correlation analysis, repeated measures analysis, and survival analysis. Research questions for which each analysis is most appropriate are described, and the underlying assumptions and rationale of the analysis, and the logic behind interpreting the results, are explained. Assumes an understanding of univariate statistics but no prior experience with multivariate statistics. Annotation c. Book News, Inc., Portland, OR (booknews.com) Chapter 1: Introduction to Multivariate Statistics. Chapter 2: Reliability and Generalizability Theory. Chapter 3: Item Response Theory. Chapter 4: Assessing the Validity of Measurement. Chapter 5: Cluster Analysis. Chapter 6: Q-Technique Factor Analysis: One Variation on the Two-Mode Factor Analysis of Variables. Chapter 7: Structural Equation Modeling. Chapter 8: Ten Commandments of Structural Equation Modeling. Chapter 9: Canonical Correlation Analysis. Chapter 10: Repeated Measures Analyses: ANOVA, MANOVA, and HLM. This work describes research questions for which the statistic is most appropriate, the underlying assumptions and rationale of the analysis, and the logic behind interpreting the results. It is designed to clarify each statistic's logic and utility rather than teach applications.