Methods for Statistical Data Analysis of Multivariate ObservationsJohn Wiley & Sons, 25 січ. 2011 р. - 384 стор. A practical guide for multivariate statistical techniques-- nowupdated and revised In recent years, innovations in computer technology and statisticalmethodologies have dramatically altered the landscape ofmultivariate data analysis. This new edition of Methods forStatistical Data Analysis of Multivariate Observations explorescurrent multivariate concepts and techniques while retaining thesame practical focus of its predecessor. It integrates methods anddata-based interpretations relevant to multivariate analysis in away that addresses real-world problems arising in many areas ofinterest. Greatly revised and updated, this Second Edition provides helpfulexamples, graphical orientation, numerous illustrations, and anappendix detailing statistical software, including the S (or Splus)and SAS systems. It also offers * An expanded chapter on cluster analysis that covers advances inpattern recognition * New sections on inputs to clustering algorithms and aids forinterpreting the results of cluster analysis * An exploration of some new techniques of summarization andexposure * New graphical methods for assessing the separations among theeigenvalues of a correlation matrix and for comparing sets ofeigenvectors * Knowledge gained from advances in robust estimation anddistributional models that are slightly broader than themultivariate normal This Second Edition is invaluable for graduate students, appliedstatisticians, engineers, and scientists wishing to usemultivariate techniques in a variety of disciplines. |
Зміст
| 1 | |
| 5 | |
3 Development and Study of Multivariate Dependencies | 62 |
4 Multidimensional Classification and Clustering | 81 |
5 Assessment of Specific Aspects of Multivariate Statistical Models | 139 |
6 Summarization and Exposure | 227 |
References | 319 |
Appendix Software | 333 |
| 343 | |
| 347 | |
Інші видання - Показати все
Methods for Statistical Data Analysis of Multivariate Observations R. Gnanadesikan Обмежений попередній перегляд - 1997 |
Загальні терміни та фрази
analysis application approach approximately assessing associated bivariate canonical Chapter choice classification clusters coefficients combinations comparing comparisons computed configuration considered coordinates correlation corresponding covariance matrix defined denotes derived described determined developed direction discussion display distance distribution Edition effects eigenvalues eigenvectors elements example Exhibit factor first function gamma given Gnanadesikan graphical groups indicated initial instance interest involved lead linear marginal maximum mean measure methods multiresponse multivariate normality null objects observations obtained original outliers pairs parameters particular points possible present principal components probability plot problem procedures proposed quantiles reason regression relative representation residuals respectively responses robust estimators sample scale scatter separate shown shows significance similar smallest space specific squared standard statistical suggested techniques transformation units univariate unknown values variables variance vector