Supplementary files: notes.pdf, hw0.pdf, hw1.pdf, hw2.pdf, testsol.pdf, hw3.pdf, hw4.pdf, hw4clar.pdf, R files (directory), rwm.html (applet).
Instructor: Professor Jeffrey S. Rosenthal, Department of Statistics, University of Toronto. Sidney Smith Hall, room 6024; phone (416) 978-4594; http://probability.ca/jeff/;
Time: Tuesdays, 6-9 pm. First class September 11. Last class December 4.
Place: Sidney Smith Hall (100 St. George Street), room 2110. (Building "SS" on campus map.)
Course Web Page: Visit probability.ca/sta410 for the latest course information and announcements.
Textbook: There is no required textbook, but students are encouraged to consult the following references. (The notes by Gray and by Jones are freely available on-line, courtesy of their authors; the other books will be held on short-term loan at the Gerstein Science Library, 7 King's College Circle.)
Tentative list of topics to be covered: Floating-Point Arithmetic, Numerical Optimisation, the EM Algorithm, Numerical Integration, Pseudorandom Number Generation, Distributional Sampling, Monte Carlo Methods, Markov Chain Monte Carlo (MCMC) algorithms, Matrix Decomposition, Nonlinear Regression, the Bootstrap, Kernel Density Estimation, Cross-Validation.
Prerequisites: Knowledge of statistical methodology at the level of at least STA302, and computer programming experience at the level of at least CSC108.
Computing: Students will be required to write computer programs using the "R" statistical software package. Statistics Dept graduate students can access R on the Statistics Dept computers; undergraduate students can access R on CQUEST. Alternatively, students can install R on the computer(s) of their choice, by downloading its "base" package (for free) from probability.ca/cran or www.r-project.org. More information is available here.
Evaluation: One in-class test (Oct. 23, 30%); one final exam (50%); homework assignments (20%). Note: test will be in room 128 of the Mining Building (170 College Street). See also the grade-related course policies.