Syllabus

STAT 505 Fall 2011

Instructor: Jim Robison-Cox
Office: 2-259 Wilson Hall
Phone: 994-5340
Email: jimrc at math dot montana dot edu
Office Hours:

M-W-F 2 pm
Computer Help Session: Thursday 4:00 pm in Wilson 1-145
and other times by appointment.
Feel free to email me, phone or come by at other times.
Just before class, however, is generally a poor time to get help.

Texts:

  1. Required:Data Analysis Using Regression and Multilevel/Hierarchical Models Gelman & Hill
  2. Recommended:
    • The Statistical Sleuth by Ramsey and Schafer. Brooks/Cole, 2002, ISBN: 978-0-534-38670-2 erratta
    • Faraway, Extending the Linear Model with R: Generalized Linear, Mixed Effects and Nonparametric Regression. Chapman Hall/ CRC, 2006
    • Venables and Ripley, Modern Applied Statistics with Splus Fourth Edition (MASS). Springer, 2004
    • Pinheiro and Bates, Mixed Effects Models in S and S-PLUS Springer, 2000
    • The R Inferno by Patrick Burns
    • If you're experienced in Java or C, then R feels quite different. This site might help, or the book R in a Nutshell by J. Adler (O'Reilly Press, 2010)

SAS and R

Topics:

  1. R Intro: install, run lm, interpret output
  2. Matrix Arithmetic, Decomposition, Generalized Inverse
  3. Least Squares Solutions to Normal Equations
  4. Gauss-Markov
  5. Generalized Least Squares
  6. Fundamentals
    • Observational vs Experiment
    • Enumerative versus Analytic Studies
    • Random vs Representative vs convenience sample
  7. G&H Chapter 3, Single level regression
    • SLR, MLR
    • Interactions
    • Stat Inference
    • graphics
    • assumptions, diagnostics
    • prediction, validation
  8. G&H Chapter 4, More regression
    • transformations
    • identifiability
    • Models for prediction
    • series of regressions by group (lmList)
  9. Continue in G&H -- logistic regression and GLMs
Significance stars in R output are outlawed! Use this option: 
  options(show.signif.stars =FALSE)
or store it in a .First file which R runs when started in this directory 
.First <- function(){
  options(show.signif.stars =FALSE)
}
save.image()
Or put the options into a text file called .Rprofile in the startup directory.
Use getwd() to see where that is.

Assessment:

A midterm test, a final, and weekly homework assignments. Each counts one-third.
Homework is due in class on the day assigned. I will accept it up to 4 pm with no penalty, after that, I'll deduct 10% per day (no credit after I post solutions or return graded homeworks). Homework average will be penalized for poor attendance and or repeated tardiness. Working with others on the homework and discussing problems with others are encouraged, but you must understand everything you write down and turn in, and you each have to go through the struggle of learning the software programs.

Conduct

Students are expected to follow the MSU rules of acceptable conduct, which basically means "don't cheat". On homeworks, I encourage you to interact with each other and working together is fine. However, you must understand everything you write down. If you use a web, written, or other resource, you must give credit to that site or author.

Jim Robison-Cox
Last Updated: