STATISTICS 427

Statistical Computing

Fall, 2007

Classes: 11:30-1:25 M, 11:30-12:10 W @ Yost 101

Instructor: Professor Jiayang Sun, Yost 326, 368-0630, jsun at case.edu

Office Hours: 1:25-2pm M, 12:10-1pm W @ Yost 326 (subject to change)

TA: Rongfang Gu, Yost 329, 368-0472, rongfang.gu at case edu

Office Hours: 1-5pm Th @ Yost 234 (368-2656) (starting on 9/6)

Other TAs' Hours: http://stat.case.edu/tutor-schedule.htm

Course Overview: Statistical computing is an essential part of modern statistical training, as it touches on almost every aspect of statistical theory and practice. This course covers some basic elements of statistical computing (numerical computation, seminumerical computation, symbolic and graphical computation) and some special topics. A tentative list of topics include:

• Introduction to computational statistics
  1. Errors
  2. Computer arithmetic
  3. Some tricks including recurrence relations
• Seminumerical computation - Stochastic simulations
  1. Examples of simulation
  2. Pseudo-random deviate
  3. Non-uniform variate generation
  4. Variance reduction methods
  5. Monte Carlo Methods for Statistics -> Special Topics
• Numerical computation
  1. Numerical linear algebra and linear regressions
  2. Integration and approximations
  3. Optimization and root finding
• Graphical and symbolic computation
  1. Graphical statistical methods
  2. Applications in Splus, Maple and Matlab
• Special Topics
  1. Jackknife and Bootstrap
  2. Gibbs sampling and Markov Chain Monte Carlo
  3. EM algorithms, Laplace Approximations ...
  4. Movies and special effects webpages?

Prerequisite: Stat 425 and some knowledge about Splus and one of the following three programming languages: Fortran, C and Pascal.

Text Books: No textbook is required since no single text covers all our topics. The course materials will be drawn from following excellent, recommended books:

• Lange (2000). Numerical Analysis for Statisticians, Springer, ISBN: 0-387-94979-8
• Gentle (2004). Elements of Computational Statistics, Springer, SBN: 0-387-95489-9.

Other References:

• Ripley, B. D. (2006). Stochastic Simulation, Reprint of 1987 original, Wiley. ISBN: 978-0-470-00960-4.
• Geof H. Givens, Jennifer A. Hoeting (2005), Computational Statistics, Wiley, ISBN: 0-471-46124-5
• Gentle (2005). Random Number Generation and Monte Carlo Methods, Springer, 2nd edition, ISBN 0-387-00178-6.
• Stewart, G. W. (1993). Afternotes on Numerical Analysis. (Do not print all pages!)
• Press et. al. (1992, 1996, 2007). Numerical Recipes: The art of scientific computing. Cambridge University Press: Cambridge. 2nd Edition (1992). 3rd edition (2007). (Do not print all pages!)

• Gentle, Ha"rdle and Mori (2004). Handbook of computational statistics. Concepts and methods. Springer-Verlag, Berlin, ISBN 3-540-40464-362-06
• Thisted, R. (1988). Elements of Statistical Computing. Chapman and Hall.

Grades:

The assessment will be based on homework assignments (50%) and a final examination (50%).

Class Webpage: http://sun.cwru.edu/~jiayang/427/

---

Jiayang Sun