Introduction to multivariate analysis : linear and nonlinear modeling / Sadanori Konishi.

Includes bibliographical references (pages 299-307) and index.

TOC Introduction Regression Modeling Classification and Discrimination Dimension Reduction Clustering Linear Regression Models Relationship between Two Variables Relationships Involving Multiple Variables Regularization Nonlinear Regression Models Modeling Phenomena Modeling by Basis Functions Basis Expansions Regularization Logistic Regression Models Risk Prediction Models Multiple Risk Factor Models Nonlinear Logistic Regression Models Model Evaluation and Selection Criteria Based on Prediction Errors Information Criteria Bayesian Model Evaluation Criterion Discriminant Analysis Fisher's Linear Discriminant Analysis Classification Based on Mahalanobis Distance Variable Selection Canonical Discriminant Analysis Bayesian Classification Bayes' Theorem Classification with Gaussian Distributions Logistic Regression for Classification Support Vector Machines Separating Hyperplane Linearly Nonseparable Case From Linear to Nonlinear Principal Component Analysis Principal Components Image Compression and Decompression Singular Value Decomposition Kernel Principal Component Analysis Clustering Hierarchical Clustering Nonhierarchical Clustering Mixture Models for Clustering Appendix A: Bootstrap Methods Appendix B: Lagrange Multipliers Appendix C: EM Algorithm Bibliography Index

"Multivariate techniques are used to analyze data that arise from more than one variable in which there are relationships between the variables. Mainly based on the linearity of observed variables, these techniques are useful for extracting information and patterns from multivariate data as well as for the understanding the structure of random phenomena. This book describes the concepts of linear and nonlinear

AS

Sagar Shahanawaz