Instructor

Syllabus

Office Hours -- Fall 2010

Class Meeting Time

Current Textbook

Courses that may serve as a prerequisite: Any of the following: PSYC 228 or 709; EDRM 710; STAT 509, 515, 700, or 704; MGSC 291, 391 or 692; BIOS 700.
(If you have had a course that may be equivalent to one of these, please contact me about it.)

More Information

• Informational Flyer about STAT J530, Fall 2010

Course Description

Purpose: To introduce students with a variety of statistical backgrounds to the basic ideas in multivariate statistics. It will cover the assumptions, limitations, and uses of basic techniques such as cluster analysis, principal components analysis, and factor analysis as well as how to implement these methods in R, SAS, and SPSS. Instead of theoretical development, the focus will be on the intuitive understanding and applications of these methods to real data sets by the students.

Instructions for Accessing Lectures Online

Available Computing Resources

Course Notes

• Class Slides for Chapter 1

• Class Slides for Chapter 2

• Class Slides for Chapter 3

• Class Slides for Chapter 4, Part 1

• Chapter 4 Slides with Variance and Covariance Derivations

• Class Slides for Chapter 4, Part 2

• Class Slides for Chapter 5

• Class Slides for Chapter 6, Part 1

• Figure 6.4 from Everitt textbook

• Class Slides for Chapter 6, Part 2

• Table of Possible Covariance Structures for Model-based Clustering

• Class Slides for Chapter 7, Part 1

• Class Slides for Chapter 7, Part 2

• Class Slides for Chapter 8

My Drawings from Class

• Drawing for PCA

• Drawing for LDA

Downloading Instructions for R

• Instructions for Downloading R

Computing Tips: Some Review

• Introduction to SAS which should be a good instruction for the software

• A link to Dr. Habing's SPSS example code for multivariate analysis

Computer Code for Class Examples

Example R Code

• Chapter 1 example R code (Mean vector, Covariance matrix, Correlation matrix, Distances, Q-Q plot, Chi-square plot)

• Chapter 2 example R code (Enhanced scatterplots, Convex hull, Chi-plot, Bivariate boxplot, Bivariate density estimator, Bubble plot, Scatterplot matrix, 3-D scatterplot, Star plot, Chernoff faces)

• A simple example of a Box-Cox transformation for multivariate data

• Chapter 3 example R code (Principal Components Analysis, including scree plots, plots of PC scores, and CIs for variances of the population PCs)

• Chapter 4 example R code (Factor Analysis, including rotations, plotting factor scores, and model diagnostics)

• Chapter 5 example R code (Multidimensional Scaling and Correspondence Analysis)

• Chapter 6 example R code (Cluster Analysis)

• Chapter 7 example R code (Hotelling T^2 inference, Discriminant Analysis, MANOVA)

• Chapter 8 example R code (Canonical Correlation Analysis, Multivariate Regression)

• Some extra examples of plots for multivariate observations (Profile plots, Profiles with bars, Andrews Plots)

Example SAS Code

• Chapter 1 example SAS code (Mean vector, Correlation matrix, Q-Q plot, Chi-square plot)

• Chapter 3 example SAS code (Principal Components Analysis, including plots of PC scores)

• Chapter 4 example SAS code (Factor Analysis, including rotations and model diagnostics)

• Chapter 5 example SAS code (Multidimensional Scaling)

• Chapter 6 example SAS code (Cluster Analysis)

• Chapter 7 example SAS code (Discriminant Analysis and MANOVA)

• Chapter 8 example SAS code (Canonical Correlation Analysis, Multivariate Regression)

Data Sets

• Fisher's Iris Data

• Air Pollution Data (from Chapter 2)

• U.S. Air Pollution Data (from Chapter 3)

• Foodstuffs Content Data (Table 3.6 of text)

• Bumpus's Bird Data

• Life Expectancy Data

• Pain Correlation Matrix and Legal Offenses Dissimilarity Matrix (from Problem 4.7 and Table 5.12 of text)

• Pottery Data (Table 6.3 of text)

• ACT items Data

• Body Measurements Data

• SAT scores Data

• SAT scores with graduation indicator

• Egyptian skulls data (from Table 5.8)

• SIDS data (from Table 7.5)

• Blood Glucose data (from Table 8.6 -- slightly corrected from book's printing which had some typos)

• Computer data

Midterm Exam Information

• Midterm: (Word document) or (pdf document) (due on or before Thursday, Oct. 21 by 4:00 p.m.)

• Concrete Data or Concrete Data with a column of ID numbers

• Sales Data or Sales Data with a column of ID numbers

Final Exam Information

• Final Exam: (Word document) or (pdf document) (due on or before Friday, December 10, by 4:00 p.m.)

• Cereal Data

• Oil Data or Oil Data with a column of ID numbers

That's a Good Question!

• Questions and Answers

Homework

• Homework 1, Fall 2010 (due on or before Wednesday, Sept. 15 by 3:00 p.m.)

• Homework 2, Fall 2010 (due on or before Monday, Oct. 4 by 3:00 p.m.)

• Homework 3, Fall 2010 (due on or before Friday, Nov. 5 by 3:00 p.m.)

• Homework 4, Fall 2010 (due on or before Tuesday, Nov. 30 by 3:00 p.m.)

Some Homework Solution Code and General Comments

• Some example R code for the Homework 1 Problems

• General Comments on Homework 1

• Some example R code for the Homework 2 Problems

• General Comments on Homework 2

• Some example R code for the Homework 3 Problems

• Some example R code for the Homework 4 Problems