An R and S-Plus(r) Companion to Multivariate Analysis

ISBN-13: 9781852338824 / Angielski / Twarda / 2005 / 221 str.

Brian Everitt

Opis

Applied statisticians often need to perform analyses of multivariate data; for these they will typically use one of the statistical software packages, S-Plus or R. This book sets out how to use these packages for these analyses in a concise and easy-to-use way, and will save users having to buy two books for the job. The author is well-known for this kind of book, and so buyers will trust that he s got it right."

Recenzje

From the reviews:

"This text is much more than just an R/S programming guide. Brian Everitt's expertise in multivariate data analysis shines through brilliantly." Journal of the American Statistical Association, June 2006

"This text concentrates on the major methods that are applied to multivariate data. ... Suitable R and S-PLUS code is presented for each technique. The data sets and the code used in the book are available for download from the web. The R and S-PLUS output is often edited in the text to improve its readability, and some 'point-and-click' features of the S-PLUS GUI are demonstrated. ... This book is suitable for applied statisticians and advanced undergraduate and postgraduate students ... exploring multivariate data." (Susan R. Wilson, Zentralblatt MATH, Vol. 1082, 2006)

"There are currently many textbooks available discussing multivariate analysis, varying from the theoretical to the applied. ... Both the statistical methods and the implementation are illustrated by numerous worked examples ... . topics are explained in a clear style illuminated by relevant examples. A strong point of the text is the careful interpretation of the example analyses. ... references are given for any reader who wishes to investigate further. ... In summary, this is an excellent book to help an R/S-SLUS user analyse multivariate data." (Stuart Barber, Journal of Applied Statistics, Vol. 33 (7), 2006)

"This book, as the title implies, is a companion to multivariate analysis ... . this one uses a wealth of practical examples to explain and demonstrate how multivariate sets of data can be analyzed using the appropriate software. ... The appendix briefly describes the main features of the packages ... . All the sets of data and code used in the book are available from the website http://biostatistics.iop.kcl.ac.uk/publications/everitt/. The text also contains a wealth of references for the reader to pursue." (S. Starkings, Short Book Reviews, Vol. 25 (2), 2005)

"This is a routine book on multivariate statistical methods. It provides a very modest amount of the basic theory and emphasises the usage of computer codes from the software R (which is of course free) and S-Plus (which is proprietary) for carrying out the most commonly available multivariate procedures. ... This book will be useful to those who wish to pick up some multivariate methods, specially those from social and related sciences. ... there are references to adequate sources for further reading." (Arup Bose, Sankhya, Vol. 68 (1), 2006)

Spis treści

Multivariate Data and Multivariate Analysis.- Looking at Multivariate Data.- Principal Components Analysis.- Exploratory Factor Analysis.- Multidimensional Scaling and Correspondence Analysis.- Cluster Analysis.- Grouped Multivariate Data: Multivariate Analysis of Variance and Discriminant Function Analysis.- Multiple Regression and Canonical Correlation.- Analysis of Repeated Measures Data.

O autorze

Brian Everitt is Emeritus Professor of Statistics, King’s College, London

Blurb

Most data sets collected by researchers are multivariate, and in the majority of cases the variables need to be examined simultaneously to get the most informative results. This requires the use of one or other of the many methods of multivariate analysis, and the use of a suitable software package such as S-PLUS or R.

In this book the core multivariate methodology is covered along with some basic theory for each method described. The necessary R and S-PLUS code is given for each analysis in the book, with any differences between the two highlighted. A website with all the datasets and code used in the book can be found at http://biostatistics.iop.kcl.ac.uk/publications/everitt/.

Graduate students, and advanced undergraduates on applied statistics courses, especially those in the social sciences, will find this book invaluable in their work, and it will also be useful to researchers outside of statistics who need to deal with the complexities of multivariate data in their work.

Brian Everitt is Emeritus Professor of Statistics, King’s College, London.