Statistics 235 – Modern Data Analysis Methods

 

 


 

 

!!!Click here for course announcements!!!

Instructor:     

Dan Gillen

Assistant Professor

Department of Statistics

Office: 2226 Donald Bren Hall (DBH)

Telephone: 949.824.9862

E-mail: dgillen@uci.edu

WebPage: http://www.ics.uci.edu/~dgillen

Office hours:      Tuesday 3:30-4:30 & Wednesday11:00-12:00,

and by appointment

 

Lectures:

 

Tuesday and Thursday, 2:00-3:20, Room: CS 243

 

Discussion:

 

Friday, 2:00-2:50, Room: DBH 1423

Prerequisites:

 

Graduate standing in Statistics or Statistics 120C or equivalent. or permission of instructor

 

Description:

 

This course will introduce a variety of modern tools for data analysis.  The course will emphasize the use of computational and resampling techniques for data analyses wherein the data do not conform to the standard toolbox of regression models and/or the complexity of the modeling problem threatens the validity of standard methods.  Topics to be considered will be bootstrap standard error estimation, smoothing for visualization of data, and prediction.  The course will focus on both theory and application of methods for data analysis. Problems will be motivated from a scientific perspective.

 

Required Text:

 

Venables WN and Ripley BD. (2003). Modern Applied Statistics with S (4th edition). Springer.

 

Supplementary texts:

 

 

á   Efron B and Tibshirani RJ. (1993). An Introduction to the Bootstrap. London: Chapman & Hall.

á   Hastie T, Tibshirani R, and Friedman J. (2001).  The Elements of Statistical Learning.  Springer.

 

Software/Computing:

 

Examples that are presented in class are primarily done using the R statistical package, and it is recommended that R be used for homework assignments and exams. R is free software which can be downloaded from the web at http://www.r-project.org/.  R can be installed onto Windows, Mac, or Unix machines. In addition, the student computer lab in CS 364 will have R loaded onto all Windows machines.  The website also offers many tutorials regarding the use of R.  If you wish, it is possible to use other commercially available software packages such as Splus, Stata, Matlab, or SAS.

 

Homework:

 

There will be a total of 5 homework assignments.  Assignments will typically be due 1 to 1.5-2 weeks from the day they are handed out.

 

Midterm Exam:

 

Tentatively scheduled for Thursday, Nov 1st.  The exam will be in-class (closed-book, closed-note), and will cover material through the Thursday, October 25th lecture.

 

Final Exam:

 

The final exam is scheduled for Thursday, Dec 13th.  The final exam will be a take-home, handed out on Thursday, Nov 29th and due on Thursday, Dec 13th by 5pm.

 

Grading:

Homework:

Midterm:

Final:

 

30%

30%

40%

Course Links:

 

 

Home

Syllabus

Reading Assignments

Course Handouts

Problem Sets

Data