This textbook presents a classical approach to some techniques of multivariate analysis in a simple and transparent manner. It offers clear and concise development of the concepts; interpretation of the output of the analysis; and criteria for selection of the methods, taking into account the strengths and weaknesses of each. With its roots in matrix algebra, for which a separate chapter has been added as an appendix, the book includes both data-oriented techniques and a reasonable coverage of classical methods supplemented by comments about robustness and general practical applicability. It also illustrates the methods of numerical calculations at various stages.This self-contained book is ideal as an advanced textbook for graduate students in statistics and other disciplines like social, biological and physical sciences. It will also be of benefit to professional statisticians.The author is a former Professor of the Indian Statistical Institute, India.
Organization of the Multivariate Data, Measures of Distance, Treatment of Missing Observations; Multivariate Normal Distribution and Related Distributions (Wishart, Hotelling's T2, Wilks'); Tests for Multivariate Normality, Robust Estimation of Location and Scale Parameters; Testing of Multivariate Hypotheses, Simultaneous Confidence Intervals; Multivariate Regression Analysis; Analysis of Variance and Covariance; Principal Component Analysis; Factor Analysis; Canonical Correlation; Classification and Discrimination.