STATISTICS 4M03/6M03

Multivariate Analysis

Course Outline 2003-2004

INSTRUCTOR

Dr P. D. M. Macdonald

Office:

HH-210

Telephone:

905 525-9140 x 23423 (24-hour Voice Mail)

e-mail:

pdmmac@mcmaster.ca

OFFICE HOURS

Monday 9:30 & 12:30, Wednesday 9:30 & 12:30, Friday 11:30.

Please come at the start of the hour. Other times by appointment.

Don't hesitate to contact me by telephone, voice mail, or e-mail any time you need help. If you need to see me at any time and my office door is open, I will see you then if I can, or arrange a time to meet later.

OBJECTIVES

Become fluent in the theory, application and calculation of multivariate statistical methods.

TOPICS

We will work through Chapters 1 to 8 of Srivastava in detail, then, as time permits, we will cover selected topics from Chapters 9 and 11.

TEXT

Srivastava, Muni. Methods of Multivariate Statistics, Wiley.

REFERENCE TEXTS

Cody, R.P. & Smith, J.K. (1997) Applied Statistics and the SAS Programming Language, Prentice Hall.
Elliott, R.J. (2000) Learning SAS in the Computer Lab, Second Edition, Duxbury
Spector, P. (1994) An Introduction to S and S-Plus, Duxbury.

LECTURE NOTES

Copies of the lecture notes will be available from the Instructor.

COURSE WEB SITE

Check the course web site at http://www.math.mcmaster.ca/peter/s4m03/s4m03_0304 regularly for announcements, assignments, course notes, and answers to frequently-asked questions.

COMPUTERS

Students are expected to use computers in this course. The course text gives SAS instruction. All of the methods studied are available in SAS, Splus and R, and some instruction in these packages will be given. Students are encouraged to explore other packages such as MINITAB and SPSS.

Our Splus licence allows students to install Splus on their home computers. See the instructor to borrow the installation disk.

ASSIGNMENTS

It is each student's responsibility to keep up to date with the course by working ahead in the text. Each chapter of the text has worked examples and lots of problems.

Three assignments will be handed in for grading. Some of the assignment questions will involve the data sets on the data disk that accompanies the text; this will give you some experience in "real-world" applications of statistics.

Students may work in pairs and submit a single copy of any assignment, in which case both students will receive the same mark.

TESTS

2003-10-30 (Thursday)

19:00-20:30

BSB-304

2003-11-20 (Thursday)

19:00-20:30

JHE-326H

Aids permitted: Any calculators; any tables, books and notes.

EXAMINATION

There will be a formal 4-hour examination in December. The examination will be held in the BSB computer laboratory so that you can use SAS, R and Splus for your calculations and graphs.

Aids permitted: Computers; any calculators; any tables, books and notes.

GRADING SCHEME FOR STATISTICS 4M03

All assignments will be counted. Only the better of the two tests will be counted. The final mark will be the best of the following four calculations:

   (A) 100% Exam;
   (B) 80% Exam + 20% Assignments;
   (C) 80% Exam + 20% Tests;
   (D) 60% Exam + 20% Assignments + 20% Tests. 

I will review all "borderline" marks and possibly make further adjustments.

STATISTICS 6M03 FOR GRADUATE CREDIT

Graduate students taking Statistics 6M03 for graduate credit must EITHER lead a 50-minute class OR submit a written report on any ONE of the following: (1) a topic that was not covered in class by the instructor; (2) the analysis of a multivariate data set (in which case the report should be a plain-language consultant's report); (3) a recent journal article on a topic of current research in multivariate methodology.

This additional work will count for 10% of the graduate student's final mark. The Statistics 4M03 mark computed from assignments, tests and examinations by the grading scheme shown above will count for 90%.

ACADEMIC ETHICS AND DISHONESTY

We remind you of the Statement on Academic Ethics found in the Senate Policy Statements distributed at registration and available in the Senate Office. Any student who infringes one of these resolutions will be treated according to published policy.


Statistics 4M03/6M03
Last updated 2003-10-30 12:33