National
Institute of Statistical Sciences
19 T. W. Alexander
Drive
P.O. Box 14006
Research Triangle Park, NC 27709-4006
Tel: 919.685.9300
FAX: 919.685.9310
admin@niss.org
News: August, 1997
Since the March 13 groundbreaking, the NISS building has remained on schedule and within budget. Completion of construction is expected by the end of September, and the building will be dedicated on November 7, 1997, in conjunction with the annual meeting of the NISS Board of Trustees.
A continuing photographic chronology of the building is available on the NISS Web site: http://www.niss.rti.org.
With the move into the new building, virtually all ways of reaching NISS will change. Effective November 1, 1997, please use the following to reach us:
| Postal Address: | P.O. Box 14006 Research Triangle Park, NC 27709-4006 |
| FedEx/UPS: | 19 T. W. Alexander Drive Research Triangle Park, NC 27709 |
| Telephone: | 919.685.9300 |
| FAX: | 919.685.9310 |
| E-mail: | lastname@niss.org |
| WWW: | www.niss.org |
Six postdoctoral fellows are joining NISS this year,,and are introduced below. As they arrive, Minge Xie (Ph.D., Statistics, Illinois, 1995), who worked on toxicological risk assessment and drug discovery at NISS, leaves to take a faculty position in the Department of Statistics at Rutgers University.
Victor De Oliveira, recipient of a Ph.D. in Statistics from the University of Maryland, College Park, will be involved with NISS research on transportation and the environment.
Elise Miller-Hooks, who received a Ph.D. in Civil Engineering from the University of Texas at Austin, will divide her time between NISS and the Department of Civil Engineering at Duke University. At NISS, she will be working on the Transportation Project, to develop computer methods for evaluation of strategies for dynamic control of traffic signals.
Karl Petty, 1997 recipient of a Ph.D. in Electrical Engineering from the University of California, Berkeley, will remain in Berkeley, collaborating with Peter Bickel and others on estimation of travel times and incident detection on freeways.
Matthias Schonlau will be based at AT&T Laboratories in Florham Park, NJ, working on network intrusion as part of the NISS Large Data Sets project. He has just completed his Ph.D. in Statistics at the University of Waterloo.
J. Alex Stark received his Ph.D. in Electrical Engineering from Cambridge University in 1995. He will join NISS in January, and will be involved in research on large data sets and information technology.
Kay Tatsuoka received the Ph.D. in Statistics from Rutgers University in 1996, and spent a year as a visiting faculty member at Ohio State University before joining NISS. He also holds a Ph.D. in mathematics from the University of Wisconsin. As part of the project on large data sets, he will collaborate with scientists from Glaxo Wellcome on drug discovery.
Chong Gu (Statistics, Purdue) is visiting NISS and North Carolina State University for the academic year 1997-98, under the auspices of the Joint NISS/Triangle Universities Visitorship Program. He will be involved in research on large data sets and automobile emissions.
Yong-Bin Lim (Statistics, Ewha Womans University, Korea), who visited NISS during 1996-97, will return for several months during the current year, with continuing involvement in the drug discovery component of the large data sets project.
Large Data Sets. The GOALI program at NSF has awarded NISS a three-year grant to conduct "Pilot Projects to Explore Large Data Sets." Alan Karr and Jerome Sacks are principal investigators.
The project comprises two interconnected pilot efforts dealing with large data sets, each involving a major industrial partner: Drug Discovery, in collaboration with Glaxo Wellcome, Research Triangle Park, NC; and Network Intrusion, partnered by AT&T Laboratories, Florham, NJ. In each instance, there are specific scientific issues with high-stakes implications for the industry at large; the available data sets are for current and prospective needs, lending immediacy to the research. At the same time, the pilot projects address long-run issues (such as heterogeneity and multiplicity) whose relevance extends beyond the corporations and industries they involve.
Key participants on the project are C. Gu (visiting NISS) Y. Lim (visiting NISS), D. Pregibon (AT&T), Y. Vardi (Rutgers), A. Wilks (AT&T), S. Young (Glaxo Wellcome) and NISS postdocs M. Schonlau and K. Tatsuoka.
Travel-Activity Synthesis. Funded by the Los Alamos National Laboratory (LANL), as part of its TRANSIMS transportation modeling system, NISS will develop statistically-based methodology to synthesize activities for households and group quarters in the metropolitan Portland, OR, region; and use this methodology to generate one or more sets of population-wide activity lists for Portland, for a single mid-week day without abnormal weather or special events.In addition, probability models for transit preferences of individuals within households, possibly dependent on activities, will be developed.
The principal products will be methodology that generates activities, computer programs implementing the methodology and activity lists generated by the programs.
Key members of the project team are R. Beckman (LANL), A. Karr (NISS), E. Pas (Civil Engineering, Duke), J. Sacks (NISS), P. Speckman (Statistics, Missouri) and D. Sun (Statistics, Missouri).
NISS had an active presence at the 1997 JSM in Anaheim. Some highlights follow, with a pictorial account available on the NISS Web page.
Throughout the meetings, a NISS information display was located in the registration area. The display outlined the structure and activities of NISS, presented photographs of the NISS building, and provided pointers to additional information.
On Sunday, August 10, as part of the new JSM invited poster session, Alan F. Karr, Associate Director, and Jerome Sacks, Director, presented a poster highlighting current NISS research, including Drug Design, Drinking Water Quality, Software Maintenance and Freeway Breakdown.
On Tuesday, August 12, an invited session, organized and chaired by Jerome Sacks, Director of NISS, featured three presentations highlighting recent NISS research. Douglas W. Nychka (NISS and North Carolina State University, currently on leave to NCAR), spoke on "Ozone: Modeling and Monitoring an Atmospheric Pollutant", Paul Speckman (NISS and University of Missouri) discussed "NISS Research on Travel Demand Forecasting", and Alan F. Karr (NISS) presented a talk on "NISS Research on Software Engineering."
On Tuesday, August 12, Minge Xie (ex-NISS postdoc, now at Rutgers University), in the session on Bayesian and Frequentist Approaches to the Analysis of Ordinal Data, presented a talk on "Regression Modeling of Ordinal Data with Nonzero Baselines," dealing with toxicological research conducted under an EPA-NISS cooperative agreement.
On Wednesday, August 13, Richard L. Smith (NISS and University of North Carolina at Chapel Hill), in the session on Environmental Epidemiology, spoke on "Assessing the Health Risk of Environmental Particulates."
The Statistical Software Engineering session on Thursday, August 14, organized by S. Eick (Bell Labs), co-director of the NISS software project, featured strong participation by several members of the project, including Adam Porter (University of Maryland), speaking on "Experiments in Software Inspection," Todd Graves (NISS postdoc), speaking on "Statistical Models of Code Decay", and J. Stephen Marron (NISS and University of North Carolina at Chapel Hill), who served as discussant.
A pictorial account is available.
NISS was co-sponsor of the Third International Conference on Knowledge Discovery and Data Mining, held in Newport Beach, CA, on August 14-17. These meeting brought together researchers from statistics, artificial intelligence and data bases with shared interests in extracting knowledge from large (often distributed) data sets.
 |
 |
| Help |