Syllabus

Statistics 410: Introduction to Statistical Computing and Regression

Fall 2004

Instructor:	William C. Wojciechowski
Office:	3018 Duncan Hall
Office Hrs:	2:30-3:30p.m. M & Appt.
E-mail:	williamc@stat.rice.edu

Required Textbooks

1. Applied Linear Statistical Models, Fifth Edition (1996) by J. Neter, M.H. Kutner, C.J. Nachtsheim, W. Wasserman. McGraw-Hill, ISBN 0-256-11736-5.

2. Modern Applied Statistics with S, Fourth Edition (2002) by W.N. Venables and B.D. Ripley. Springer, ISBN 0-387-95457-0

Description

Statistics 410 is an applied statistics course dealing with applications of regression and analysis of variance (ANOVA) models. Both fixed effects and random effects will be presented. If time permits, an introduction to modeling categorical responses (e.g., binomial and Poisson) will be given. Applications may include epidemiology, genetics, botany, engineering, psychology, sociology, economics, and business. Both observational studies and experiments will be covered. For our purposes, the term "statistical computing" in the title of the course refers to the use of statistical software to implement and to apply the models. The main statistical packages we will use are S-Plus and R. Splus is a commercial software package that is available on Owlnet and the Statistics Department’s computers. R is a language and environment for statistical computing and graphics very similar to S-Plus. R is free software available from the R Project homepage (http://www.r-project.org/). Modern Applied Statistics with S will serve as a reference for using Splus and R. There is no prerequisite in computing for this course.

The emphasis of the course will be on applications. Theory will be covered, but only when it sheds light on the methodology. A working knowledge of differential and integral calculus is necessary and some background in matrix algebra is desirable but not required.

Class webpage: http://www.owlnet.rice.edu/~stat410/

General Topics – Selected from Applied Linear Statistical Models

• Simple Linear Regression
• Multiple Linear Regression
• Analysis of Variance
• Experimental Design

Course Requirements

Weekly assignments, projects, and examinations will constitute the basis for your grade. The relative weighting is given below. You can expect weekly textbook assignments and two data analysis projects. There will be a midterm examination and a comprehensive final examination.

Component	Assignments	2 Projects	Midterm	Final
Percentage	15	25	30	30