WSS
NEWS

News about activities of the Washington Statistical Society
A Chapter of the American Statistical Association


WSS Home | Newsletter | WSS Info | Seminars | Courses | Employment | Feedback | Join!

November 2001

Contents:



The 2001 Morris Hansen Lecture

The Washington Statistical Society is pleased to announce the eleventh in the annual series of lectures to honor the memory of Morris Hansen. This lecture series is made possible by a grant from Westat, where Morris Hansen was senior statistician for 20 years and served as Chairman of the Board of Directors at the time of his death. Details are available in seminars.

The eleventh Morris Hansen lecturers are Warren Mitofsky and Murray Edelman. Warren Mitofsky is the president of Mitofsky International, conducting election surveys word-wide. He was a founder of the television networks' election consortium. He started the CBS/NY Times Poll, introducing probability methods to election coverage, including the first exit poll. He and Joseph Waksberg developed the first random digit dialing (RDD) telephone sampling. He has served as president of the American Association for Public Opinion Research, the National Council on Public Polls, and the Research Industry Coalition. He is a fellow of the American Statistical Association.

Murray Edelman is Editorial Director of Voter News Service, a pool of ABC, CBS, CNN, FOX, NBC, and the Associated Press, where he is responsible for the exit polling and election estimation. He is responsible for estimates of winners in 500 separate elections, and for exit polls of 100,000 voters on Election Day. He was Associate Director at CBS News, where he helped develop the statistical models used for elections. He is past president of the American Association for Public Opinion Research. He received his PhD from the University of Chicago in 1973.

Return to top


2001 FCSM Research Conference
November 14-16, 2001

The Federal Committee on Statistical Methodology (FCSM) Research Conference will be held on November 14-16, 2001 at the Key Bridge Marriott in Arlington,Va. The conference will open with a plenary session on "The Interplay Between Research Innovation and Federal Statistical Practice," featuring Stephen Fienberg, Carnegie Mellon University. The 2001 FCSM Research Conference is being sponsored by various Federal government statistical agencies and hosted by the Council of Professional Associations on Federal Statistics.

Although conference registration and $150 fee was due by September 28, 2000, periodic updates concerning the conference may be found on the website, www.fcsm.gov. Additional information may be obtained from Stephen H. Cohen, Office of Survey Methods Research, Bureau of Labor Statistics, Room 4915, Washington, DC 20212; Phone: 202-691-7400, Fax: 202-691-7426, and E-mail: fcsm@census.gov.

Return to top


Conference on Confidentiality, Disclosure, and Data Access

Theory and Practical Applications for Statistical Agencies

January 7-9, 2002
U.S. Bureau of Labor Statistics
Washington, DC

Sponsored by:
U.S. Census Bureau
U.S. Bureau of Labor Statistics
American Statistical Association (ASA)
  Committee on Privacy & Confidentiality
Federal Committee on Statistical Methodology
Government Statistics Section of the ASA
Washington Statistical Society
  Council of Professional Associations on Federal Statistics

Data Dissemination vs Confidentiality Protection

There is a fundamental tension at the heart of every statistical agency's mission. Each is charged with collecting high quality data to inform National policy and enable statistical research. This necessitates dissemination of both summary and microdata. Each is also charged with protecting the confidentiality of survey respondents. This often necessitates blurring the data to reduce the probability of the reidenti-fication of individuals. The trade-off dilemma, which could well be stated as protecting confidentiality (avoiding disclosure), but maximizing access, has become more complex as both technological advances and public perceptions have altered in an information age. Fortunately, statistical disclosure limitation techniques have kept pace with the rapidly growing changes affecting data access and dissemination

This Conference highlights the progress that statistical agencies are making in addressing these challenges from both a theoretical and practical standpoint.

A Pre-Conference primer is offered to provide a baseline for the uninitiated. Then, to kick off the Conference, we have asked leaders from some of the U.S. Federal statistical agencies to participate in a high level discussion on confidentiality policy. Those sessions are followed by two days of invited paper sessions describing the current state-of-the-art.

PRELIMINARY PROGRAM



Monday, January 7, 2002

Pre-Conference Workshop -- Sponsored by Federal Committee on Statistical Methodology's (FCSM) Confidentiality and Data Access Committee:
  • Privacy, Confidentiality and the Protection of Data - A Statistical Perspective.-- For those not grounded in the techniques or terminology of confidentiality and data access, but who are interested in attending the conference, there is a workshop preceding the substantive sessions.

  • Federal Agencies Discuss Confidentiality Policy -- Sponsored by the FCSM's Subcommittee on Privacy and Confidentiality. Two sessions address key questions:

  • Restricted Data -- What is confidentiality? What are the real threats to confidentiality? Should users accept responsibility for ensuring confidentiality?

  • Restricted Access -- When to use licenses vs. data centers? How do we deal with perceptions that data are not adequately protected? Should we set up federal data centers? and, Is remote access safe?

INVITED SESSIONS

Tuesday and Wednesday, January 8-9, 2002
  • Where We Are
    • Summary of Methods in Use
    • Challenges of Technology
  • New Advances with Demographic Data
    • Measuring Disclosure Risk
    • Disclosure Methods and Information Loss for Microdata
    • Disclosure Methods and Information Loss for Tabular Data
  • New Advances with Economic and Linked Data
    • New Research with Tabular Data
    • Disclosure Risk, Non-Perturbative Disclosure
    • Control Methods and Information Loss for Tabular Data
    • Disclosure Limitation in Longitudinal Linked Data
  • Data Access Methods
    • Licensing
    • Secure Sites
    • Remote Access
  • Perceptions
    • Confidentiality Perceptions
    • Ethnographic Research
    • Perception Issues in the Economic/ Organizational Sector

New Book Presents State-of-the-Art Solutions

The U.S. Census Bureau and Elsevier Science of Reed Elsevier, Inc. are pleased to announce the upcoming release of Confidentiality, Disclosure and Data Access: Theory and Practical Applications for Statistical Agencies, edited by Pat Doyle, Julia Lane, Jules Theeuwes, and Laura Zayatz. This new book presents the latest developments in statistical data protection methodology and application. The Conference by the same name brings the authors of the book to Washington, DC to discuss their work, providing a review of the new state-of-the-art techniques that directly address confidentiality, disclosure, and data access from both a theoretical and a practical perspective.

All Conference participants will receive a copy of the new book Confidentiality, Disclosure, and Data Access --Theory and Practical Applications for Statistical Agencies.

Specifics about the Conference

The Intended Audience
  • Civil servants in national statistical agencies
  • Statistical practitioners
  • Social scientists using secondary data
Location
Conference Center
Bureau of Labor Statistics
2 Massachusetts Avenue, NE
Washington, DC 20212

Registration
Fee: $150.00 (USD)
Due: December 3, 2001
Contact: Anna Holaus or Daneeta Stewart on (301) 457-2308 (Fax: (301) 457-3682)

Hotel Information
Phoenix Park Hotel
Washington, DC
For Reservations Call: (202) 638-6900 or 1 (800) 824-5419
Reference Group No. 8961 when making your reservations.

First Come, First Serve

Limited Seating

For Registration and Hotel Information Contact Anna Holaus or Daneeta Stewart

For Other Information Contact Pat Doyle at patricia.j.doyle@census.gov

For your convenience, we now have a web site containing the brochure and registration form for the conference on confidentiality and data access (www.census.gov/srd/sdc/index.html). The site links to other sites of interest including the publisher of the book Confidentiality, Disclosure, and Data Access -- Theory and Practical Applications for Statistical Agencies where you can obtain more information on obtaining a copy of the book when its released. (Note, conference attendees will receive a copy of the book as part of their conference materials.)

Specific questions about the program can be directed to Pat Doyle at patricia.j.doyle@census.gov. Questions on registration can be directed to Anna Holaus or Daneeta Stewart as noted earlier.

Return to top


57th Annual Deming Conference

The star-studded array of speakers for the 57th Annual Deming Conference in Atlantic City New Jersey December 10-14 includes Frank Harrell, Ramon Littell, George Milliken, Jeff Wu, Jason Hsu, Stu Hunter, Stanley Lemeshow and Paul Mielke for the tutorials.

The short courses include a one day course by David Ruppert on "Measurement Error in Nonlinear Models", Kathleen Kerr on "Experimental Design and Statistical Analysis of Spotted Microarrays" and Warren Gish on "Challanges Posed by the Human Genome Project".

Topics include multiple comparisons with applications to clinical trial, statistical methods for clinical trials, permutation methods, statistical process control, regression modeling strategies, sequential clinical trials, advances in experimental design and repeated measures analysis of covariance. Most of the topics are based entirely or in part on recent texts by the speakers that our offered through the conference at considerable discounts.

Registrants attending the sessions can get continuing education units for the conference by request.

Available texts include:

  • Multiple Comparisons: Theory and Methods by Hsu
  • Analysis of Messy Data Volume III by Milliken and Johnson
  • Measurement Error in Nonlinear Models by Carroll, Ruppert and Stefanski
  • Statistical Methods for Clinical Trials by Norleans
  • SAS Systems for Linear Models 4th Edition by Littell
  • Permutation Methods: A Distance Function Approach by Mielke and Berry
  • Regression Modeling Strategies with Applications to Linear Models, Logistic Regression and Survival Analysis by Harrell.
  • Applied Logistic Regression 2nd edition by Hsmer and Lemeshow
  • Experiments: Planning, Analysis, and Parameter Design Optimization by Wu and Hamada
  • Statistical Control: By Monitoring and Feedback Adjustment by Box and Luceno


This programme is jam packed with interesting state-of-the-art statistical methodology of interest to all statisticians and particularly those in pharmaceuticals and quality assurance. Get all the details, registration forms and information, abstracts and textbook pricing and order forms at our web site http://nimbus.temple.edu/~kghosh/deming01/.

Return to top


Education Announcements

American University
Department of Mathematics and Statistics

Graduate and undergraduate programs in statistics at American University provide training at all levels in theoretical and applied statistics. The programs are designed for both full and part time students, with all required courses offered after 5 p.m. Graduate courses offered include Mathematical Statistics, Probability, Sampling, Regression, Design of Experiments, Applied Multivariate Analysis, Time Series, Nonparametric Statistics, Data Analysis, Statistical Software, Stochastic Processes, Statistical Inference, Multivariate Analysis, Statistical Computing, Linear Estimation, and Special Topics.

Ph.D. in Statistics

Admission to the program generally requires a master's degree in statistics, although those with a master's in a related field can be admitted subject to evaluation of their professional experience or additional course work.

Specializations include: Adaptive designs, categorical data analysis, clinical trials, exact inference, computational statistics, environmental statistics, forensic statistics, nonparametric regression, response-driven designs, stable distributions, statistical genetics, and time series.

Small classes and personal attention provide an excellent opportunity for individualized professional growth. Graduates of the Ph.D. program are employed in universities, government agencies, and private industry.

M.S. in Statistics

The master's degree program requires a sound background in mathematics, but it is possible to make up prerequisites once provisionally admitted. The thirty-hour program provides an excellent background for those who want to move into more advanced positions requiring substantial theoretic and applied statistical training. It is also a sound foundation for a doctoral program at American University or elsewhere.

M.S. in Statistics for Policy Analysis

This program is especially useful for those with an undergraduate degree in social sciences or humanities who want to be able to do substantial applied statistical work and who are interested in the policy implications of their results. Six hours of the thirty-hour program consist of course work in a policy area such as public administration, political science, economics, sociology, education, or international relations.

TEACHERS:
The master's programs are particularly well suited for secondary school or community college mathematics teachers who want to be better able to teach statistics as well.

CAREER CHANGERS: Are you interested in a second career in teaching at the secondary or collegiate level? In addition to the above degree programs, American University offers a program unique in the Washington area:

Ph.D. in Mathematics Education

One of the few mathematics education programs located within a department of mathematics and statistics, this degree can be tailored to meet individual needs. Course work is primarily in mathematics and statistics, together with nine hours specifically in mathematics education. Admission to the program requires a master's degree in mathematics, statistics, or mathematics education, although those with master's degrees in related fields can make up prerequisites once admitted to the program. Graduates of this program currently are on the faculties of community colleges, four-year colleges and research universities, are working as supervisors in K-12 systems, or are employed in educational research in industry or government.

Certificate Programs

American University offers certificate programs in applied statistics at both the undergraduate and graduate level. Each requires fifteen hours of course work at the appropriate level. Credits earned in certificate programs can be transferred into degree programs.

B.S. in Statistics

Because required courses are offered in the evening, American University also provides an opportunity to complete an undergraduate degree on a part time basis.

Combined B.S.-M.S. programs

Five-year undergraduate-graduate programs are offered in a number of combinations of mathematics, statistics, computer science and physics.

LOCATION

American University is located in northwest Washington at the intersection of Massachusetts and Nebraska Avenues. Ample parking is available on campus, and shuttle access is provided from the AU-Tenleytown Metro stop (Red Line). There are computing labs open 24 hours a day.

SOME FINANCIAL AID AVAILABLE FOR SPRING 2002 AND FALL 2002.

OPEN HOUSE AND THE OPPORTUNITY TO VISIT CLASSES:
Monday, November 12, 4:30-8:00 p.m.
For more information, call 202 885 3120, e-mail mgray@american.edu or visit our web site www.american.edu.

Return to top


Education Announcements

2002-2003 Bureau of Labor Statistics Dissertation Fellowships

The Bureau of Labor Statistics (BLS) dissertation fellowship program is designed to encourage graduate students in statistics, economics, and survey methodology to develop interests and begin research in areas of survey design and analysis. The BLS anticipates funding two fellowships per year.

Eligibility Criteria

Applicants for fellowships must have successfully passed their departmental Ph.D. qualifying examinations, and should have completed almost all coursework. Applicants must submit detailed research proposals for competitive evaluation by a peer review board representing the BLS and academia. The proposals should be in topics of interest to the BLS, such as the design and analysis of complex sample surveys, small domain estimation, nonresponse, measurement error, price index theory, seasonal adjustment, or economic measurement.

Conditions of Appointment and Benefits

Dissertation fellows will conduct their research at the Washington DC headquarters of the BLS. The researchers will be employees of the BLS. Salary is commensurate with qualifications and experience. Full-time salary will generally be at the GS-11 level (currently $44,352 - $57,656 per year). Benefits include health and life insurance, a 401(k) type pension plan, and paid vacation. Travel between the BLS and the home university on a periodic basis is expected, and will be financed by the BLS. The fellowship appointment is expected to be for one year full time (starting anytime between May 15 and December 31, 2002). Extensions of the fellowship for up to one additional year are possible. U.S. citizenship is required.

Applications

The application deadline is December 1, 2001. The following information is required of all applicants. 1) A letter of interest outlining the proposed research (1-2 pages). 2) Graduate school transcript and three letters of recommendation. Initial screening of applicants will be carried out by BLS researchers with expertise in statistics, economics, and survey methodology. Applicants will be evaluated on academic performance, the scientific merit of the proposal, the feasibility of the proposed work, and the value of the proposed research to the BLS and the academic community. Candidates passing this first screening will be asked to submit a detailed research proposal by March 1, 2002. These detailed proposals will be peer reviewed by a panel composed of BLS and academic researchers.

For further information or to submit applications, please contact:

For Students in Statistics and Survey Methodology:

Dr. John Eltinge
Bureau of Labor Statistics
2 Massachusetts Avenue NE
Suite 1950
Washington DC 20212
Eltinge_J@bls.gov
Fax: (202) 691-7426

For Students in Economics:

Dr. James Spletzer
Bureau of Labor Statistics
2 Massachusetts Avenue NE
Suite 4945
Washington DC 20212
Spletzer_J@bls.gov
Fax: (202) 691-6425

Return to top


September, 2001 - June 2002 SIGSTAT

September 19, 2001
Time Series Forecasting System in SAS/ETS
November 14, 2001
What's New in SAS 8
December 12, 2001
PROC BOXPLOT & UNIVARIATE in SAS/STAT
January 9, 2002
Output Delivery System (ODS) in SAS
February 13, 2002
PROC VARMAX in SAS/ETS
March 13, 2002
R for Windows
April 10, 2002
PROC GAM in SAS/STAT
May 8, 2002
SAS INSIGHT
June 12, 2002
PROC KDE in SAS/STAT


SIGSTAT is the Special Interest Group in Statistics for the CPCUG, the Capital PC User Group, and WINFORMS, the Washington Institute for Operations Research Service and Management Science.

All meetings are in Room 3056, 1800 M St, NW from 12:30 to 1:30. Enter the South Tower & take the elevator to the 3rd floor to check in at the guard's desk.

First-time attendees should contact Charlie Hallahan, 20 Announcements2-694-5051, hallahan@ers.usda.gov and leave their name. Directions to the building & many links of statistical interest can be found at the SIGSTAT website, www.cpcug.org/user/sigstat/

Return to top


Note From The WSS NEWS Editor

Items for publication in the January 2001 WSS NEWS should be submitted no later than November 27, 2001. E-mail items to Michael Feil at michael.feil@usda.gov. Any items received after this date will appear in the next issue of the WSS NEWS.

Return to top


[an error occurred while processing this directive]

Return to top


WSS Home | Newsletter | WSS Info | Seminars | Courses | Employment | Feedback | Join!

First posted October 29, 2001
Last modified November 03, 2015

http://washingtonstatisticalsociety.org/newsletters/wss0111.shtml

Webmaster: Dan Jacobs, Maryland Sea Grant