STP 526 Syllabus, Fall 2009

Course: STP 526, Theory of Statistical Linear Models

Location: 3:30-4:45 Monday and Wednesday, Discovery Hall (formerly known as Agriculture) Room 123

Instructor: Dr. Sharon Lohr, PS A 444,  965-4440, sharon.lohr@asu.edu    Home page: http://stat.asu.edu/~lohr

Office hours:  1:30-3:00 Monday, Wednesday; and by appointment. You may also ask questions at any time through e-mail.

Prerequisite:  STP 421, STP 427 and MAT 342 are required prerequisites. No exceptions will be made.

Text:  A First Course in Linear Model Theory by Nalini Ravishanker & Dipak Dey

Grading Policy: Final grade is based on 70% exams, 30% homework (lowest homework score is dropped)

Final Exam: Wednesday, December 16 (12:10 – 2:00 pm). I cannot reschedule the final exam for students; if you cannot take the final exam for a good reason (vacation plans or wanting to leave early are not considered “good reasons”) you need to get approval from the dean of the college.

Assignments: Assignments and projects will be due at the beginning of class. Late homework is not accepted, but your lowest homework score will be dropped in computing your final grade.

Computing: We shall use the R package for statistical computing. This is free software that runs on Unix, Windows, or Mac OS. You can download the software to your laptop from www.r-project.org

ASU's Policy on Academic Dishonesty: In the “Student Academic Integrity Policy” manual, ASU defines “Plagiarism [as] using another's words, ideas, materials or work without properly acknowledging and documenting the source. Students are responsible for knowing the rules governing the use of another's work or materials and for acknowledging and documenting the source appropriately.”  You can find this definition at: http://www.asu.edu/studentaffairs/studentlife/judicial/academic_integrity.htm#definitions

Academic dishonesty, including inappropriate collaboration, will not be tolerated. There are severe sanctions for cheating, plagiarizing and any other form of dishonesty.

Policy on Incompletes: You will only be given a grade of Incomplete if all of the following statements apply to you: a) The circumstances which make it impossible for you to complete the course before the end of the semester are beyond your control and occurred within the last two weeks of the semester. b) You have been in attendance through most of the course. c) You have a passing grade on the work completed. d) You have written documentation (a doctor's excuse, for example) of your need for an Incomplete.

Topics:

  1. Review of Linear Algebra (chapters 1-2)
  2. Generalized Inverses (chapter 3)
  3. The General Linear Model (chapter 4)
  4. Multivariate Normal Distribution (chapters 5-6)
  5. Inference in the General Linear Model (chapter 7)
  6. Regression Diagnostics and Robust Regression (chapter 8)
  7. Mixed-effects Linear Models (chapter 10)

Additional References:

Christensen, R. (2002). Plane Answers to Complex Questions, 3rd ed. New York: Springer-Verlag.
Faraway, J. (2005). Linear Models With R. Boca Raton, FL: Chapman & Hall. (This is an applied book on how to do regression with R.)
Graybill, F.A. (1983). Matrices with Applications in Statistics, 2nd ed. Belmont, CA: Wadsworth.
Graybill, F.A. (1976). Theory and application of the linear model. North Scituate, MA: Duxbury
Harville, D.A. (1997). Matrix Algebra from a Statistician’s Perspective. New York: Springer.
Hocking, R.R. (1985). The Analysis of Linear Models, Brooks/Cole.
Hocking, R.R. (2003). Methods and Applications of Linear Models, 2nd ed. New York: Wiley.
Jorgensen, B. (1993). The Theory of Linear Models. New York : Chapman & Hall.
Rencher, A. (2000). Linear Models in Statistics. New York: Wiley.
Searle, S. (1971). Linear Models, New York: Wiley.