next up previous index
Next: asa.stat.comp.04 Up: ASA Statistical Computing (5 Previous: asa.stat.comp.02


Sponsoring Section/Society: ASA-COMP

Session Slot: 2:00- 3:50 Wednesday

Estimated Audience Size: 100

AudioVisual Request: None

Session Title: Internet Developments

Theme Session: No

Applied Session: Yes

Session Organizer: Narasimhan, Balasubramanian Stanford University

Address: Department of Statistics Stanford University Stanford, CA 94305

Phone: 650-725-6163

Fax: 650-725-8977


Session Timing: 110 minutes total (Sorry about format):

First Speaker - 25 minutes Second Speaker - 25 minutes Third Speaker - 25 minutes Fourth Speaker - 25 minutes Discussant - 10 minutes

Session Chair: Narasimhan, Balasubramanian Stanford University

Address: Department of Statistics Stanford University Stanford, CA 94305

Phone: 650-725-6163

Fax: 650-725-8977


1. SticiGui: Statistics Toolbox for Internet and Classroom Instruction with a Graphical User Interface

Stark, P.B.,   University of California, Berkeley

Address: Deptartment of Statistics University of California Berkeley, CA 94720-3860

Phone: 510-642-1430

Fax: 510-642-7892

Email: stark@stat.Berkeley.EDU

Abstract: SticiGui is a collection of online course material, including a hypertext with links to a glossary, embedded Java applets to illustrate statistical concepts and analyze data, online interactive lab assignments, automated assignment grading, and logging and querying of student scores to a web site. The material is introductory and largely non-mathematical, but includes case studies in which statistics has been involved in litigation or legislation, and a number of real data sets. For a preview, visit stark/Teach/SticiGui97/index.htm . The content is still rough and by no means finished. I will demonstrate the material, and relate some student reactions and some of my experiences using this online approach to teach large (250-350 student) lower-division classes.

2. WebStat: What's New in Version 2!

Ogden, R. Todd,   University of South Carolina

Address: Department of Statistics University of South Carolina Columbia, SC 29208

Phone: 803-777-7800

Fax: 803-777-4048


West, R. Webster, University of South Carolina

Abstract: Introduced in the spring of 1997, WebStat is a complete statistical package written in the form of a Java applet for access over the World Wide Web (WWW) or as a stand-alone application. The package has been used as the primary analysis package in several courses around the world. A brief history of the development of WebStat is given, along with the developers' responses to user feedback. The current and future capabilities of WebStat will be dicussed.

3. Introductory Statistics on the Internet via PHP

de Leeuw, Jan,   University of California at Los Angeles

Address: Department of Statistics University of California at Los Angeles 8142 Math Sciences Bldg, Box 951554, Los Angeles, CA 90095-1554

Phone: 310-825-9550

Fax: 310-206-5658


Abstract: On, there is a calculator that replaces classical statistical tables. In fact, it can do much more. We have calculator pages for the cumulative distribution, for the quantile function, for the probability density/probability mass function. These pages are available for normal, logistic, cauchy, laplace, student, noncentral student, exponential, gamma, chi square, noncentral chi square, f, noncentral f, weibull, beta, uniform, binomial, poisson, negative binomial, discrete uniform, and hypergeometric distributions.

In addition, the calculator can make either point, line, or spike plots of both the cdf and the pdf. Finally, it can sample an arbitrary number of random numbers from the distributions, and email them to the user.

Technical appendix: the calculator uses the C code from Barry Brown et al's dcdflib and randlib. On top of this C code, functions were written to integrate the statistics into PHP/FI, a WWW scripting language. PHP/FI, thus extended, was linked as an Apache module into the WWW server. Thus the statistical functions can be used directly on the html pages. If you want to know more about implementation, see

4. Distributed Computing for Data Analysis

Lang, Duncan Temple,   Bell Labs, Lucent Technologies

Address: Bell Labs, Lucent Technologies 700 Mountain Avenue, Room 2C-259 Murray Hill, NJ 07974-2070

Phone: 908-582-3217

Fax: 908-582-3340


Hansen, Mark, Bell Labs

Chambers, John, Bell Labs

Abstract: Statistical computing is part of a more general process, which can be called computing with data . Besides traditional statistical analysis, this involves acquiring, organizing, and visualizing data, often in large, structured datasets organized in database management systems and used for purposes beyond analysis. An important challenge for statistical computing (and statistics in general) is to increase the scope of our involvement in this diverse environment. At the same time, the computing environment itself is becoming more diverse in all respects: data and users are widely spread and using many different systems.

We describe research looking towards the next generation of software for such applications, centered on the idea of distributed computing with data . By this we mean distributed in two fundamentally different, but related, senses. First, the data and the tasks users apply to the data are distributed geographically, over a heterogeneous network of computers and operating systems. Second, the programming environment we envision is distributed over a variety of languages and other software.

The system we are designing is centered on the idea of communication of tasks, data description, and application implementation to support distribution in both senses. The support for communication is provided by existing software (CORBA in one trial project, e.g.). The data-analytic programming and, especially, the structure of the relevant data objects, make use of the latest version of S. By combining the features of such software, we expect to provide user/programmers with a more flexible and extensible environment, with many more choices for implementing new ideas. This allows programmers to develop specialized applications in their chosen language and have these provide services to and receive services from other applications locally or via the web. In addition, we anticipate important opportunities to automate much of the data and method definition, exploiting the self-describing nature of classes and methods in S and IDL.

Discussant: Rosenberger, James L.   Penn State University

Address: Department of Statistics 326 Thomas Building Penn State University University Park, PA 16802-2111

Phone: 814-865-1348

Fax: 814-863-7114


List of speakers who are nonmembers: None

next up previous index
Next: asa.stat.comp.04 Up: ASA Statistical Computing (5 Previous: asa.stat.comp.02
David Scott