Modeling With R 

30 January -20 Feb  2009  

Aim of the Course: This 3-week course will show you how to use R to create models for use in classification and prediction. You will be introduced to advanced graphing methods as needed. Modeling techniques include OLS, LAD, and EIV regression, quantile regression, and decision trees (CART).  Model validation is emphasized.

Who Should Take This Course: Anyone familiar with R who encounters statistics in their work and wishes to program their own procedures in a convenient, widely-used, open source (free) language. 

Instructor: Dr. Phillip Good, former Calloway Professor of Computer Science at the University of Georgia (Fort Valley) and graduate of the program in mathematical statistics at UC Berkeley, is the author of Introduction to Statistics via Resampling Methods and R (Wiley, 2005), Common Errors in Statistics (and How to Avoid Them) (Wiley, 2003 with James Hardin), Resampling Methods (Birkhauser, 2nd ed, 2005), Permutation, Parametric, and Bootstrap Tests of Hypotheses (Springer, 3rd ed, 2004), Manager's Guide to Design and Conduct of Clinical Trials (Wiley, 2002), and Applying Statistics in the Courtroom (CRC, 2001). He has given tutorials at the Joint Statistical Meetings (U.S.) and Deming Conference, lectured in Belgium, France, Holland, Ireland, and Spain, and was a traveling lecturer for the American Statistical Association. This is his fifth (5th) year of providing on-line interactive courses. 

Prerequisite: Prerequisite: You should have familiarity with basic statistical concepts or the equivalent.  You should have some familiarity with R as in Introduction to R. 

Organization of the Course: The course takes place over the Internet.  During each course week, you participate at times of your own choosing - there are no set times when you must be online. Course participants will be given an alias and access to a private bulletin board that serves as a forum for discussion of ideas, problem solving, and interaction with the instructor. The course is scheduled to take place over three weeks. Estimated weekly time requirements for this course - an hour and half for the lecture, an hour and a half for preparation, and another three hours for homework and review.  At the beginning of each week, participants receive the relevant material, in addition to answers to exercises from the previous session. During the week, participants are expected to go over the course materials and work through exercises. Discussion among participants is encouraged. The instructor will provide answers and comments.

Optional Text: Participants may wish to purchase and make use of Introduction to Statistics via Resampling Methods and R/S-Plus (Wiley, 2005; Chapter 7). 

1. Session I: Linear Regression and Advanced Graphics
   
   Ordinary Least Squares
   
   Interpretation of Output
   
   Plotting residuals, Plots with multiple lines, Side-by-side plots
   
   Stepwise Regression
   
   
2. Session 2: Alternatives to OLS Regression
   
   Deming Regression
   
   LAD
   
   Quantile Regression
   
   
3. Session 3: Decision Trees
   
   Construction, Pruning, Prediction
   
   Validation Methods

        Trees vs. Regression

        Which Modeling Technique?

One week is allowed after Session 3 to give participants the opportunity to clarify any questions arising from this or previous sessions.

Cost of course is $300.  If you register before July 5th, you need pay only $225. In either case, students, faculty and research workers at academic institutions are eligible for a further discount of $50.  Just send an email to courses@statisticsonline.info from your academic email account to receive a discount coupon.

Immediately after your payment is credited, you will receive an email giving you a password, sign up instructions, and the web address (URL) of the course material.  Note that you will not be able to access this address until the start date of the course.