“Practical Design of Generalized Likelihood
Ratio Control Charts for Autocorrelated
Federal Committee on
Data.” The proposed approach is based
on automatic time series identification
and estimates the GLR control limits via
Statistical Methodology
stochastic approximation using boot-
strap resampling. This ability to take into
Statistical Policy Seminar
account the uncertainty of the underlying
model is an important step forward. Good
Beyond 2010: Confronting the Challenges
performance is found on both simulated
and actual data.
The method of steepest ascent is com-
November 18–19, 2008
monly used in response surface studies to
move to regions with better outcomes.
With a single response variable, the meth-
The Ninth in a Series of Seminars Hosted by COPAFS
od is simple and direct. What to do when
(The Council of Professional Associations on Federal Statistics) there is more than one response is con-
Participants will include statisticians, economists, and managers, as well as
sidered in “Steepest Ascent for Multiple
professionals in the broader statistical community who share an interest in
Response Applications,” by Robert W.
Mee and Jihua (Regina) Xiao. Three per-
keeping current on issues related to federal data.
tinent questions are answered in this paper.
Keynote Address: Hermann Habermann, Consultant First, for multiple response applications,
Location: L’Enfant Plaza Hotel, 480 L’Enfant Plaza, SW, Washington, DC 20024
what search directions are inferior and can
be excluded from consideration? Second,
Cost: $195
what graphical tools can assist in our
understanding the tradeoffs and choosing
For further information, call (703) 836-0404, email
copafs@aol.com, or
a compromise direction for exploration?
fax (703) 836-0406.
Third, do compromise directions exist that
ensure improvement in all responses?
The registration form is available at
www.copafs.org.
Peter Z. G. Qian, Huaiqing Wu, and
C. F. Jeff Wu develop “Gaussian Process
Models for Computer Experiments With
Topics:
Qualitative and Quantitative Factors.”
• Statistical Uses of Administrative Records in Federal Agencies
Gaussian process models have proven very
• Case Studies in the Statistical Uses of Administrative Records
effective in modeling data from computer
• Cell Phones: The New Frontier in RDD Surveys
experiments with quantitative factors. This
article extends the approach so it can be
• New Perspectives and Practices on Nonresponse Bias Analyses
used when some factors are categorical.
• Current Issues in Privacy and the Safekeeping of Personally Identifiable A special class of correlation functions is
Information suggested and an iterative estimation pro-
• Survey Respondent Incentives
cedure is developed. The method is illus-
trated with a simulated example and a real
• Current Trends in Access to Restricted-Use Data
application modeling the thermal distribu-
• Development and Management of Human and Institutional Capital in Statistical
tion of a data center.
Organizations
S. R. Dalal and C. L. Mallows close out
• 2010 Census Experiments the issue with an article about an interesting
• Issues of Data Capacity and Statistical Quality to Support Modeling and
problem in reliability, “Optimal Stopping
Microsimulation Efforts
With Exact Confidence on Remaining
Defects.” The authors derive a new class of
• Making Survey Processes More Robust in Response to Funding Reductions
stopping rules that can be used to bound,
• Using Paradata to Improve the Management of Survey Costs
at a stated probability level, the number of
faults that remain in a product based on
Support provided by:
the times when faults are discovered dur-
Agency for Healthcare Research and Quality
•
Bureau of Economic Analysis
•
Bureau of Justice Statistics ing a testing phase. Such rules could be
Bureau of Labor Statistics
•
Bureau of Transportation Statistics
•
Energy Information Administration
useful to buyers of software who are test-
Environmental Protection Agency
•
National Agricultural Statistics Service
•
National Center for
Education Statistics
•
National Center for Health Statistics
•
Office of Research, Evaluation, and Statistics
ing for faults, to buyers of large lots who
of the Social Security Administration
•
Statistics of Income Division of the Internal Revenue Service
are screening for defectives, or to database
U.S. Census Bureau
•
Science Resources Statistics/National Science Foundation
engineers who are converting a database
from one schema to another. n
14 AMSTAT NEWS AUGUST 2008
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68