Welcome to CSI 771

Computational Statistics

Instructor: James Gentle See Computational Statistics

Fall, 1994


PostScript versions of all of the lectures, ASCII files of data, and other files are available for downloading by anonymous ftp at
science.gmu.edu
After logging in to the ftp site, change to the directory jgentle/csi771.

Lecture 1:

Course overview; method of communication
Computer organization: Unix and basic tools; S-Plus
Computational statistics
Monte Carlo studies
Random number generation in S-Plus

Lecture 2:

More on Monte Carlo simulation
Random number generation
Random number generation from non-uniform distributions
*Summaries of two articles due
5-minute presentations

Lecture 3:

Some preliminaries on use of TeX, Emacs, etc.
More on random number generation
*Design for Monte Carlo study due
5-minute presentations

Lecture 4:

Nonparametric density estimation
*Feasibility study -- software, etc. due
5-minute presentations

Lecture 5:

Some additional comments on Monte Carlo methods
Nonparametric density estimation

Lecture 6 was a review of the midterm.

Lecture 7:

Resampling: jackknife and more on bootstrap
*Review and critique of a fellow student's paper due
5-minute presentations by reviewers

Lecture 8:

Cross validation

Lecture 9:

Gibbs sampling
*Revised paper due

Lecture 10:

Other topics in computational statistics:
Classification and regression trees
Projection pursuit

Lecture 11:

Other topics in computational statistics:
ACE
Graphical display of multivariate data


The final exam is in two parts.
  • Take home
  • The in class part has questions related to the individual projects.

    Computational Resources

    Labs with Unix workstations are available for use in this class in both CSI and SITE.
  • CSI facilities.
  • Software available in SITE labs.

    Other Resources

    It will be necessary to use Unix for assignments and the project, so some familiarity with it is necessary.

    The most important WWW repository of statistical stuff (datasets, programs, general information, connection to other sites, etc.) is StatLib Index at Carnegie Mellon.