Multivariate data appear in all scientific fields of investigation and the study of multivariate analysis has become central to the discipline of data science. Not only is it part of the statistical education curriculum but it is also an essential tool for applied scientists in their research work. An Introduction to Multivariate Data Analysis clearly explains how to successfully reduce a large and complex set of data with many variables to a manageable new formulation where information, structure and underlying patterns are more clearly revealed. This book is an accessible and comprehensive introduction to the subject of multivariate analysis, and will appeal to all those students and researchers who would benefit from the use of multivariate methods to analyse data from their experiments and studies. A basic knowledge of univariate statistics and matrix algebra is assumed.
Table of Contents
Introduction. Matrix algebra. Basic multivariate statistics. Graphical representation of multivariate data. Principal components analysis. Biplots. Correspondence analysis. Cluster analysis. Multidimensional scaling. Linear regression analysis. Multivariate analysis of variance. Canonical correlation analysis. Discriminant analysis and canonical variates analysis. Loglinear modelling. Factor analysis. Other latent variable models. Graphical modelling. Data mining.
Trevor F. Cox is Senior Statistician at Unilever Research and Development, Port Sunlight and Visiting Professor at University of Reading, UK.