Computer-Aided Multivariate Analysis, Fourth Edition

I'm writing about the 2nd ed. (1990), but if you landed here, I think what I have is of value for later editions too. The book is fantastic. There are a myriad of technical terms for various kinds of multivariate analyses. The average person has no idea what the names mean -- or how to choose between them! To be able to DO anything (right, anyway) you need a CONCRETE understanding. Such is what this book provides. Right off the bat, the book tells you -- not only what kind of data each technique requires -- but what questions you might ask (and want answered) for such data. So, in a mere 4 pages -- near the beginning! -- you get 1 or 2 paragraphs on each of these: factor analysis, discriminant analysis, cluster analysis, multiple linear regression, principal components analysis, and more. You'll know what these techniques require as input (what kinds of data situations) and what they assume the question(s) is/are that you want answered -- already concrete, already good understanding of the differences of the formerly cryptic technique names in a mere 4 pages! I have seen no other book do this. The rest of the book is nearly as effective in the decoding of other details of the multivariate analyses. In short, start with this book, because therein you will be way way ahead in acquiring a perspective on multivariate analyses with little effort. Go to any other book(s) first and you may eventually develope a perspective -- only by accident, that is with little author help -- after a long hard road. Get your perspective from the get-go instead -- with this book.

Often, students and researchers need to perform multivariate statistical analyses on their data. Unfortunately, a lack of mathematical training prevents many from taking advantage of advanced techniques, in part, because books focus on the theory and neglect explaining how to perform and interpret multivariate analyses on real-life data. Computer-Aided Multivariate Analysis is a welcome exception, helping students choose the appropriate analyses for their data, carry them out and interpret the results. Only a limited knowledge of statistics is assumed and geometrical and graphical explanations are used to explain what the analyses do. However the basic model is always given and assumptions are discussed. In this edition the computer emphasis is enhanced by the inclusion of three additional statistical packages written for the personal computer. The authors also discuss data entry, database management, data screening, data transformations, as well as multivariate data analysis. This third edition contains a new chapter on log-linear analysis of multi-way frequency tables.

While this book will not teach you all you need to know about any of the techniques to be an expert, it WILL teach you enough to read research, and to learn what the various techniques do. The mathematical level is moderate, and the emphasis is on practical applications. Highly recommended for grad students in the social sciences