Sponsoring Section/Society: ASA-COMP
Session Slot: 8:30-10:20 Thursday
Estimated Audience Size: 40-60
AudioVisual Request: None
Session Title: Computer Algebra Systems in a Course in
Probability and Statistics
Theme Session: No
Applied Session: Yes
Session Organizer: Kinney, John Rose-Hulman Institute of Technology
Address: Rose-Hulman Institute of Technology 5500 Wabash Avenue Terre Haute, IN 47803
Phone: 812-877-8390
Fax: 812-877-3198
Email: john.kinney@rose-hulman.edu
Session Timing: 110 minutes total (Sorry about format):
Opening Remarks by Chair - 5 or 0 minutes First Speaker - 30 minutes (or 25) Second Speaker - 30 minutes Third Speaker - 30 minutes Discussant - 10 minutes (or none) Floor Discusion - 10 minutes (or 5 or 15)
Session Chair: Kinney, John Rose-Hulman Institute of Technology
Address: Rose-Hulman Institute of Technology 5500 Wabash Avenue Terre Haute, IN 47803
Phone: 812-877-8390
Fax: 812-877-3198
Email: john.kinney@rose-hulman.edu
1. MAPLE Integrated Into the Instruction of Probability and Statistics
Address: Department of Mathematics Hope College Holland, MI 49422-9000
Phone: 616-395-7527
Fax: 616-395-7123
Email: tanis@math.hope.edu
Abstract: You can use a Computer Algebra System (CAS) such as MAPLE to enhance instruction in probability and statistics. Change parameters of various probability models to illustrate graphically their significance. Make figures that are static in a book come alive using animation. Use the integration or summation capabilities of a CAS to solve interesting problems. Simulate random phenomena to illustrate theoretical concepts. Let a CAS find and graph the p.d.f.'s of order statistics. Use a CAS to simulate the first m (only) out of n order statistics. Involve the students.
2. Mathematica as an Aid in Teaching Probability and Statistics
Kinney, John, Rose-Hulman Institute of Technology
Address: Rose-Hulman Institute of Technology 5500 Wabash Avenue Terre Haute, IN 47803
Phone: 812-877-8390
Fax: 812-877-3198
Email: john.kinney@rose-hulman.edu
Abstract: Examples are given in the use of Mathematica in introductory courses in probability and statistics. Mathematica, as well as other computer algebra systems, allows the instructor to make probability and statistics more visual than has been possible in the past. Calculations are also eased, allowing a de-emphasis on approximations to probability distributions. Classroom tested examples are given. Examples include; probability distributions and their graphs; central limit theorem; bivariate normal distributions; generating functions, estimation problems and distributions of sample statistics.
3. GAUSS; a Fast, Flexible, Comprehensive Programming Language for Scientists, Engineers, and Statisticians
Heller, Barbara, Illinois Institute of Technology
Address: Department of Pharm. and Phys. Sciences University of Chicago, Abbott Hall 947 E. 58th Street Chicago, IL 60637
Phone: 773-834-0378
Fax:
Email: bheller@midway.uchicago.edu
Abstract: The best way to describe GAUSS is that it is a fast and flexible interactive comprehensive programming language. It is the solution for those who do not have the time or the inclination to program in C, FORTRAN, or other languages since it is easy to learn and at the same time flexible and powerful for sophisticated analyses. On the one hand GAUSS is exceptionally fast, providing performance comparable to compiled C or FORTRAN programs. On the other hand it saves you the trouble of progamming from scratch because it contains a large number of built-in procedures such as mathematical and statistical function evaluation, differentiation and integration, linear algbra operations, eigenvalues, Fourier transforms, and random number generation. Also included are GAUSS Applications programs for various specific uses. Of particular interest is a module for maximum likelihood estimation along with an additional set of procedures for statistical inference. Another module of interest is CurveFit which includes procedures for the nonlinear least squares fitting of data with or without weighting. Additional procedures provide for computing bootstrap estimates and distributions. GAUSS also generates 2-D and 3-D publication quality graphs.
List of speakers who are nonmembers: None