Welcome to CSI 779

Topics in Computational Statistics:

Data Partitioning and Resampling

Instructor: James Gentle

Spring, 1995

This server will expand as the semester progresses.

PostScript versions of all of the lectures, ASCII files of data, and other files will be available for downloading either through Mosaic or by anonymous ftp at
science.gmu.edu
After logging in to the ftp site, change to the directory jgentle/csi779.

In addition to a number of smaller assignments, there will be a project that each student will have to complete for the class.

You can view or download the PostScript versions of the lectures as they are available.

January 23

Lecture 1: Basics of Monte Carlo studies; basics of S-Plus

January 30

Lecture 2: Introduction to the bootstrap.
Student descriptions of Monte Carlo studies in literature.
  • Project milestone: Student reports on two articles in statistics literature that report Monte Carlo studies

    February 6

    Lecture 3: Use of Mosaic, html, Emacs, TeX; More bootstrap fundamentals.
    Discussion of Monte Carlo experiments reported in the literature.
  • Project milestone: Design a plan to replicate and extend one of the studies

    February 13

    Lecture 4: The ideal bootstrap; Monte Carlo bootstrap.
    Bootstrap applications in time series and regression.
  • Project milestone: Feasibility study -- software, etc.

    February 20

    Lecture 5: A bootstrap estimate of bias.
    Balanced resampling Monte Carlo bootstrap.

    February 27

    Lecture 6: Jackknife, bias correction, generalized jackknife

    March 6

  • Project milestone: Present preliminary report of Monte Carlo study

    March 20

  • Midterm exam (in class)
  • Project milestone: Review and critique a fellow student's paper

    March 27

    Discussion of midterm
    Presentation and discussion of project reviews (by the reviewer)

    April 3

    Lecture 7: Bootstrap confidence intervals: percentile, BCa, ABC

    April 10

    Lecture 8

    April 17

  • Project milestone: Revise paper based on review

    April 17 and 24

  • Project milestone: Presentations

    May 1

    Lecture 9 (preliminary): Basics of Edgeworth expansions and applications

    Distribution of take-home portion of final exam.
    Data for final exam.

    May 15

    In-class portion of final exam

    Assignments

    There will be a number of short assignments during the semester.

    If you would like, you can put information about your project or your assignments (or about yourself) in your WWW page in your directory in

    /usr/local/etc/httpd/htdocs/csi779
    You only need to know a little html to do this.

  • Assignment 1 due February 13 (postponed from Feb 6)
    Data for assignment 1
    A solution for assignment 1

  • Assignment 2 due February 13
    A solution for assignment 2

  • Assignment 3 due February 20

  • Assignment 4 due February 27

  • Assignment 5 due April 10

  • Assignment 6 due April 17

    Students

    The students in the class are:

  • Amrut Champaneri

  • Michael Feil

  • David Marchette

  • John Mixon

  • Dan Rope

  • Thomas Sullivan

    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 and S or S-Plus for assignments and the project, so some familiarity with them is necessary. Some notes on these systems and the html markup language are available.
  • Unix

  • S (or S-Plus)
  • html

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

    James Gentle, jgentle@gmu.edu