Discriminant Analysis and Clustering -- Copyright -- PREFACE -- Contents -- CHAPTER 1 INTRODUCTION -- CHAPTER 2 METHODS -- 2.1 INTRODUCTION -- 2.2 METHODS OF DISCRIMINANT ANALYSIS -- 2.2.1 General Remarks -- 2.2.2 Classical Two-group Linear Discriminant Analysis -- Relation to Regression Analysis -- Tests of Hypotheses -- Advantages of the LDF -- Variable Selection -- 2.2.3 Classification Into One of Several Populations -- 2.2.4 Heterogeneous Covariance Matrices Case -- The Quadratic Discriminant Function -- Best Linear Discriminant Function -- 2.2.5 Two-group Classification by Logistic Regression -- Strengths and Weaknesses -- 2.2.6 Kernel and Nearest Neighbor Methods -- 2.2.7 Classification Trees -- 2.3 METHODS OF CLUSTER ANALYSIS -- 2.3.1 General Remarks -- 2.3.2 Algorithms -- 2.3.3 Perspective -- CHAPTER 3 THEORY -- 3.1 INTRODUCTION -- 3.2 THEORETICAL ISSUES IN DISCRIMINANT ANALYSIS -- 3.2.1 Introduction -- 3.2.2 The Fisher Linear Discriminant and Some of Its Children -- 3.2.3 Estimating Misclassification Costs -- 3.2.4 Nonparametric Techniques -- 3.3 STATISTICAL THEORY IN CLUSTERING -- 3.3.1 Introduction -- 3.3.2 High Density Clusters -- 3.3.3 Agglomerative Methods for High Density Clusters -- 3.3.4 Single Linkage, the Minimum Spanning Tree and Percolation -- 3.3.5 Mixtures -- 3.3.6 The Number of Clusters: Modes -- 3.3.7 The Number of Clusters: Components -- 3.3.8 Ultrametric and Evolutionary Distances -- CHAPTER 4 SOFTWARE AND ALGORITHM IMPLEMENTATION -- 4.1 INTRODUCTION -- 4.2 DISCRIMINANT ANALYSIS -- 4.2.1 Linear and Quadratic Discriminant Functions -- 4.2.2 Review of Packages -- P-STAT -- SPSS-X -- BMDP7M -- SAS PROCEDURES -- Other Packages -- 4.2.3 Logistic Regression -- 4.2.4 Classification Trees -- 4.3 CLUSTER ANALYSIS -- 4.3.1 Collections of Subroutines and Algorithms -- Statistical Packages Containing Clustering Software.

4.3.2 Cluster Analysis Packages -- 4.3.3 Simple Cluster Analysis Programs -- 4.4 NEEDS -- CHAPTER 5 CLOSING PERSPECTIVE -- REFERENCES.