Time: Monday, Wednesday, Friday at 11:00 AM - 11:50 AM
Location: Douglas Hall 316
Instructor: Jie Yang
Office: SEO 539
Phone: (312) 413-3748
E-Mail: jyang06 AT math DOT uic DOT edu
Office Hours: Monday, Wednesday, Friday at 12:50 p.m. - 1:50 p.m. (or by appointment)
Textbook: Geof H. Givens and
Jennifer A. Hoeting,
Computational Statistics,
John Wiley & Sons, Inc., 2005.
Preview table of contents and preface.
Buy it at Amazon
or at Wiley.
Course Contents: EM Optimization Methods, Simulation and Monte Carlo Integration, Markov Chain Monte Carlo, Bootstrapping, Nonparametric Density Estimation, Bivariate Smoothing
Prerequisite: STAT 411 or consent of instructor.
Homework:
Turn in every Wednesday before class;
half of the grade counts for completeness;
half of the grade counts for correctness of one selected problem.
Midterm: October 3, Friday, 11:00 a.m. - 12:00 p.m.
Project: Students are required to work in groups on course projects and submit their final reports before November 17th, Monday, 11:00 a.m..
Each group should consist of at most two students. The projects may come from the optional problems assigned
by the instructor or be proposed by the students themselves upon the approval of the instructor. The top three groups evaluated by the instructor
will be invited to present their results in class or in office hours.
Final Exam: December 11, Thursday, 10:30 a.m. - 12:30 p.m., Douglas Hall 316
Grading: Homework 20%, midterm 15%, project 40%, final exam 25%
Grading Scale: 90% A , 80% B , 70% C , 60% D
Format of All Exams: Exams are mainly based on the homework and the examples discussed in class. The last class session before each exam is a review session. Please prepare any questions that you may have.
No makeup exam will be given without a valid excuse.
| WEEK | SECTIONS | BRIEF DESCRIPTION |
| 08/25 - 08/29 | Introduction; 6.1; 6.2 | Introduction to the Monte Carlo method; Simulation |
| 09/01 - 09/05 | Holiday; 6.2; 6.2 | Simulation |
| 09/08 - 09/12 | 6.3; 6.3; 6.3 | Variance reduction techniques |
| 09/15 - 09/19 | 1.7; 7.1; 7.1 | Markov chains; Metropolis-Hastings algorithm |
| 09/22 - 09/26 | 7.2; 7.2; 7.3 | Gibbs sampling; Implementation |
| 09/29 - 10/03 | 9.1; Review; Midterm | The bootstrap principle |
| 10/06 - 10/10 | 9.2; 9.2; 9.2 | Basic methods |
| 10/13 - 10/17 | 9.3; 9.3; 9.7 | Bootstrap inference; Permutation tests |
| 10/20 - 10/24 | 4.1; 4.2; 4.2 | Missing data, marginalization, and notation; The EM algorithm |
| 10/27 - 10/31 | 4.2; 4.3; 4.3 | The EM algorithm; EM Variants |
| 11/03 - 11/07 | 10.1; 10.2; 10.2 | Measures of performance; Kernel density estimation |
| 11/10 - 11/14 | 10.2; 10.3; 10.3 | Kernel density estimation; Nonkernel methods |
| 11/17 - 11/21 | 11.1; 11.2; 11.2 | Predictor-response data; Linear smoothers |
| 11/24 - 11/28 | 11.3; 11.4; Holiday | Comparison of linear smoothers; Nonlinear smoothers |
| 12/01 - 12/05 | 11.4; 11.5; Review | Nonlinear smoothers; Confidence bands |
| 12/08 - 12/12 | Exam week | (Final exam) |