PART I. EXPLORATORY MULTIVARIATE TECHNIQUES: "DATA MINING" | ||
CONTENT |
LEARNING MATERIAL | |
1. Multivariate Data And Multivariate Statistics |
||
1.1 Introduction |
|
|
1.2 Types of Data |
||
1.3 Basic Multivariate Statistics |
||
1.4 The Aims of Multivariate Analysis |
||
2. Exploring Multivariate Data Graphically |
||
2.1 Introduction |
* Introductory
Notes and Graphics Notes. * R Graphics Examples Directory. Includes code for faces, stars, and coplots * SAS Face and Star Plot Directory * The Parallel Coordinate Explorer A Java Applet allowing direct manipulation of data (on automobile models) shown in the form of a parallel coordinate plot. Exercise: Starting with the default display, select first the Japanese cars, then the European, then the American ones. How do these groups differ on the other variables? Select the 8-cylinder cars. Where are they produced? * Data/Statistical Graphics Gallery Some examples of the Best and Worst of Statistical Graphics. * Notes for beginning Linear Algebra and Graphics * MVA Notes * Notes on Graphical Displays * Read MV Graphics Articles on E-Reserve |
|
2.2 The scatterplot |
||
2.3 Scatterplot Matrix |
||
2.4 Enhanced Scatterplots |
||
2.5 Coplots and Trellis Graphics |
||
2.6 Probability Plots |
||
2.7 Other Plots |
||
3. Principal Components Analysis |
||
3.1 Introduction and Motivation |
*
PCA Notes * Fieller PCA Notes * R Examples for Principal Components Analysis (PCA) * SAS Examples for Principal Components Analysis (PCA) * |
|
3.2 Presentation of Method |
||
3.3 Extensions |
||
3.4 Graphical Methods |
||
3.5 Applications and Examples |
||
4. Correspondence Analysis |
||
4.1 Introduction and Motivation |
* Read Africa CA Article
on E-Reserve |
|
4.2 A Simple Example |
||
4.3 Two-Dimensional Tables |
||
4.4 Applications |
||
4.5 Multiple Correspondence Analysis |
||
5. Multidimensional Scaling (MDS) |
||
5.1 Introduction and Motivation |
* F Young MDS
Notes * Cornell MDS Notes * Statsoft Notes * Proc MDS Documentation in SAS * Proc MDS Overview * Proc MDS Example in SAS * SAS MDS Examples |
|
5.2 Proximity Matrices |
||
5.3 Classical MDS |
||
5.4 Metric LS MDS |
||
5.5 Non-metric MDS |
||
5.6 Non-Euclidean metrics |
||
5.7 Three-way MDS |
||
5.8 Inference in MDS |
||
6. Cluster Analysis |
||
6.1 Introduction and Motivation |
* StatSoft
Text Notes on Cluster Analysis |
|
6.2 Agglomerative Hierarchical Clustering Techniques |
||
6.3 Optimization Methods |
||
6.4 Finite Mixture Models for Cluster Analysis |
mixture distributions |
|
PART II. CONFIRMATORY MULTIVARIATE TECHNIQUES[1]: "DATA CRAFTING" |
||
7. The Generalized Linear Models (GLM) |
||
7.1 Linear Models |
* Logistic
Regression Lecture Notes * PA 765: Logistic Regression Notes * * Logistic Links * SAS Logistic Regression Programs * |
|
7.2 Non-linear Models |
||
7.3 Link Functions, Error Distributions |
||
8. Regression and MANOVA |
||
8.1 Introduction and Motivation |
* SAS MANOVA
Programs * MANOVA Notes * MANOVA Resource Site |
|
8.2 LS Estimation and ANOVA models |
||
8.3 Direct and Indirect Effects |
||
9. Log-Linear and Logistic Models |
||
9.1 Introduction and Motivation |
|
|
9.2 MLE |
||
9.3 Transition Models |
||
10. Multivariate Response Models |
||
10.1 Introduction and Motivation |
|
|
10.2 Repeated Measures |
||
10.3 Multivariate Tests |
||
10.4 Random Effects |
||
10.5 Logistic Models |
||
10.6 Marginal Models for Binary Response |
||
10.7 Marginal Modelling |
||
10.8 Generalized Random Effects |
||
11. Discrimination, Classification, and Pattern Recognition |
||
11.1 Introduction and Motivation |
* SAS Discriminant
Analysis Programs * CART Examples in R * SAS CHAID Analysis Programs * Neural Network and other Example Data * Weka Website * Data Mining Notes * Tiberius Software Download Site (and information) * Neural Net Notes * Archaeology Neural Net Example |
|
11.2 Example |
||
11.3 Allocation Rules |
||
11.4 FisherŐs Discriminant Function |
||
11.5 Assessing Discriminant Function |
||
11.6 Quadratic Discriminant Function |
||
11.7 More than Two Groups |
||
11.8 Logistic Discrimination |
||
11.9 Variable Selection |
||
11.10 Other Methods |
||
11.11 Pattern Recognition, Neural Networks |
||
12. Exploratory Factor Analysis |
||
12.1 Introduction to Factor Analysis |
* SAS Exploratory FA Programs * FA and SEM Notes *SEM FAQ |
|
12.2 Basic Factor Analysis Model |
||
12.3 Estimation of the FA Model |
||
12.4 Rotation of Factors |
||
12.5 Estimating Factor Scores |
||
12.6 Factor Analysis vs. PCA |
||
13. Confirmatory Factor Analysis and Structural Equations Models | ||
13.1 Introduction | * SAS SEM Programs * SEM Notes * Proc Calis Information * Proc Calis Examples * Proc Calis Information * UCLA Proc Calis Examples * * |
|
13.2 Path Analysis & Path Diagrams | ||
13.3 Structural Equations Models (SEM's) | ||
13.4 Assessment of Fit | ||
A. Linear Algebra |
||
A.1 Matrix Algebra |
* S Rathbun
Lin Algebra Notes * N Fieller Introductory Notes |
|
A.2 Basic Linear Algebra |
*
Linear Algebra Notes. * MV parameters and sample estimates. * More Linear Algebra Notes. * Linear Algebra Notes. |
|
A.3 Eigenvalues & Eigen vectors |
* Eigenvalue / Eigenvector * Demonstration Modules * Notes about SAS and Eigenvalues and Eigenvectors * SAS code, program for matrix algebra demonstration * R Examples for Linear Algebra and Eigenvectors |
|
A.4 Distance |