Instructor: Michael Minnotte
Office: Lund 201-C
Phone: 797-2844 (office)
E-mail: Mike dot Minnotte at usu dot edu
Office Hours: TR 9:30 - 10:20, W 10:30 - 11:20, or by appointment.

Text: Analyzing Multivariate Data, J. Lattin, J.D. Carroll, and P.E. Green, (Duxbury, 2003).

Assignments 7-11 are now available in front of my office.

Room change! I have arranged to switch classrooms to Natural Resources 105. We will start meeting there Thursday, February 8. See you there!

I'll put announcements here. Please check regularly, especially if you have to miss class for any reason.

• Homework 1 (Word) - Radiology data
• Homework 2 (pdf) - Lost work days data
• Homework 3 (pdf) - Leslie Salt Property data, Radiology data, Bank Salary data
• Homework 4 (pdf) - Track and Field Record data, "Need for Cognition" Survey data, Vocational Interest Correlation, Teen Drug Use Correlation
  • R function to import triangular correlation matrices (read.tri)
• Homework 5 (pdf) - MBA Students' Car Attitudes Survey data, Nine Psychological/Intelligence Tests' Correlation,
• Homework 6 (pdf) - Nine Psychological/Intelligence Tests' Correlation, "Need for Cognition" Survey data
• Homework 7 (pdf) - British Town Distances, Nation Similarities Data, Grocery Purchase Similarities Data
• Homework 8 (pdf) - International Food Usage Data
• Homework 9 (pdf) - Brother Head Size Data, Women's Health and Attitudes Data, Workplace Characteristic and Worker Satisfaction Data
• Homework 10 (pdf) - Attitude - Intention - Behavior Data, Math Attitudes Data
• Homework 11 (pdf) - Depression Questionnaire Data

• Final Project (pdf)

• Introduction to R (Same as Homework 1)
• Data Import
• R Graphics
• Vector and Matrix Geometry - With Output
• Regression - With Output
• Principal Component Analysis - With Output
• Exploratory Factor Analysis - With Output
• Confirmatory Factor Analysis - With Output
• Multidimensional Scaling - With Output
• Hierarchical Clustering - With Output
• Distance Measures - With Output
  • kth Nearest Neighbor Distance Function
• K-Means Clustering - With Output
  • k-Means Clustering Pseudo-F Statistic Function
  • k-Means Clustering Prediction Function
• Canonical Correlation Analysis - With Output
• Structural Equation Modeling - With Output
• Discriminant Analysis - With Output
  • Prediction Plot (2-D case)
• Classification Trees - With Output
  • Some basic material on classification (and regression) trees
• Random Forests - With Output
  • Some material on random forests

• Iris Data:
  • Text File
  • Text File (with variable names)
  • SAS Xport File
  • SPSS File
  • S-Plus Object
  • Excel File
  • Excel Comma Separated Value File
• Women's Heights and Weights
• Leslie Salt Property Values
• Trivariate data for Principal Components Analysis Example
• Gross State Product Data (Raw)
• Planetary Data
• Pain Reliever Perceptions Data
• Luxury Car Perceptions Data (Lower Correlation Matrix)
• Expert Ratings of Wine-Growing Areas' Status Data
• European City Distance Data
• Car Dissimilarity Data
• Teen Drug Use Correlation Data
• Belly Dance Example Data
• Grocery Marketing Data
• Self Esteem/Job Satisfaction Correlation Matrix
• Respondent and Friend Aspirations Correlation Matrix
• South African Heart Disease Data
• Finland Alcohol Study
• New Food Item Marketing Study
• Ad Copy Likability/Intent Data
• Social Skills Study Data

• The Comprehensive R Archive Network
• Windows R Setup Executable Download - click on rwXXXX.exe, where XXXX gives the version number
• The Omega Hat Project (software connecting R with other packages)
• R Commands (Web site organized by topic)
• R Frequently Asked Questions (FAQ) List
• Understanding R (Web tutorial)
• R for Beginners (72 page pdf file)
• An Introduction to R (100 page pdf file)
• Data Analysis and Graphics Using R -- An Introduction (112 page pdf file)

Note: If you are using R on campus, you will probably need to execute the following commands to get through the firewall to install additional packages:

Sys.putenv("http_proxy"="http://proxy.usu.edu:80/")
Sys.getenv("http_proxy")

You will probably need to run these commands (on the R console) at the beginning of your session before trying to install packages.

Course Objectives: The objective of this class is to give you an introductory working knowledge of multivariate data analysis so that you can understand the literature and be able to appropriately analyze many types of multivariate data. The emphasis will be on developing a sound understanding of the methods and of when they should and should not be employed. Verbal and geometrical explanations will be stressed and only a minimal amount of mathematical notation will be used.

Prerequisites: Stat 3000 and Stat 5100. In exceptional cases, the prerequisites may be waived, but you are expected to have a good background in general statistics, regression, and statistical computing. If you are concerned about your preparation, please come see me.

Homework: I will assign homework every 1-2 weeks, usually from the text book. Please make things easy on me and yourself; make your homeworks easy to read and grade. Use one side of the paper, write or type neatly, and leave plenty of space. I will not grade a paper which I can't read. Also, show your work. Full credit will not, in general, be given for just the answer. If your answer is wrong, you will probably receive partial credit if you show your work, but not otherwise.

Many of the problems will involve computer work (see below). For the computational portions of such problems, I will want to see the commands and output of the R computer package. Cut-and-paste from the R console window into a text editor or word processor, or use the save to file command to save the entire console so that you may work with your results later. Feel free to delete mistakes or unnecessary commands and output.

Finally, you may help each other with your homeworks, but I expect what you turn in to be your own work. Helping does not mean simply copying what someone else has put down.

Late Homeworks: All homework will be due in class on the due date. The grade for the homework will be reduced by 10% if it is turned in late on the due date, and another 10% for every working day it is late after that, to a minimum of 30% of the original grade.

Once during the semester, I will, on request, waive the late penalty for a paper turned in by the class one week after the due date (or start the clock then for a still later turn-in). Simply note the request at the top of your homework when turning it in. Additional requests for extension without penalty will not be granted, so save this for a time you really need it.

Computer Use: We will use the R computer package. R is a Gnu-license (freeware) clone of the S-Plus package, and is available for free download (Windows and Unix) from http://cran.us.r-project.org/ . I will spend some time in class going over the use of R.

R is also available in most, if not all, of the computer labs on campus.

Final Project: Instead of a final exam, I will assign a final project. This will count for 25% of your grade and will consist of an analysis of a dataset of your choosing. You will need a large dataset (at least 100 cases and 10 variables) about which you know enough to formulate some real-world questions. I'll give more information later, but if you don't have such a dataset already, be on the lookout for one.

Grades: For each person I will compute an overall score according to the formula

and will assign grades accordingly. There is no fixed grade profile for this class: if everyone does well, everyone can get an A.

Disability Policy: If a student has a disability that will likely require some accomodation by the instructor, the student must contact the instructor and document the disability through the Disability Resource Center, preferably during the first week of the course. Any requests for special considerations relating to attendance, pedagogy, taking of examinations, etc. must be discussed with and approved by the instructor. In cooperation with the Disability Resource Center, course materials can be provided in alternative formats - large print, audio, diskette or Braille.

Late Adds: The last day to add this class is January 29. Attending this class beyond that date without being officially registered will not be approved by the Dean's Office.

The above schedule and procedures in this course are subject to change in the event of extenuating circumstances.