for validation. But, when the purpose is to investi-
Call for Proposals
gate responses to hypothetical scenarios, data-based
validation may be limited to model components or
high-level model summarization or equilibrium
NsF, CBMs
state, and some form of process validation will
have to be supplied. Defining an adequate set of
Announce
constructs for agent-based model validation is an
open challenge.
Other challenges articulated by the partici-
Conference series
pants from their varied disciplinary vantage points
included the need for well-grounded, agent-based
models in dynamic scenarios where the conditions
T
he National Science Foundation will hold
four conferences jointly with the Conference
Board of the Mathematical Sciences in the
in which the agents act are rapidly changing and/or
spring and summer of 2009. The conferences,
the agents, themselves, are evolving as they ‘learn.’
which aim to stimulate interest and activity in
Escalating computational complexity for such
mathematical research, include the following:
models highlights the need to understand whether/
when/how to combine modeling power of (deter-
Mathematical and Numerical Treatment of
ministic) equation-based models with (stochas-
Fluid Flow and Transport in Porous Media
tic) agent-based models when inferences are to be
drawn at several levels, from micro (agent) to macro
Cluster Algebras and Applications
(process summary, high) levels.
The Interplay Between Convex
Applying statistical thinking to the realm of
Geometry and Harmonic Analysis
agent-based modeling to draw inferences with
attached probability statements requires reexamina-
Probabilistic and Combinatorial
tion in terms of the classical statistical questions. If
Approach in Analysis
an agent-based simulation is an experiment, what
is the experimental unit? What constitutes a single
Each of the five-day conferences will feature 10
test? How are prior distributions for parameters
lectures on a topic of important current research
specified? How is variation quantified? Most impor-
in a focused area of the mathematical sciences. A
tantly, how can the scientific process of agent-based
monograph will be published afterward.
modeling be formulated so the duality between the
Also, proposals for 2010 conferences will be
theoretical model specification and the experimen-
accepted until April 24, 2009. When submitting
tation is not circular?
a proposal, keep in mind the four distinguishing
Clearly, the workshop met the objective for a
characteristics of the conference series, as follows:
NISS Explorations Workshop: to raise questions
worthy of serious research investment by investi-
Focus on a single, important, and timely
gating a scientific or policy area of current inter-
area of research by a leading practitioner
est or potential impact to determine whether the
development of new statistical approaches, novel
Publish monograph afterward for a wide audience
implementation of existing statistical technologies,
or new collaborative ventures could enable major
Provide strong emphasis on local research activity
advances in that area. A more complete discussion
of these observations and challenges for statistical
research is forthcoming at
www.niss.org.
Review all proposals for quality, breadth,
NISS inaugurated the Explorations series early
and timeliness
in 2008 with a workshop called Data Availability
—Making Research Data Public: Intelligible or
Colleges or universities with research compe-
Just Available? The workshop was held at AAAS
tence in the field of the proposal are eligible to sub-
in February. An invited session for JSM 2009 will
mit a proposal. Institutions interested in upgrading
present a reprise of the workshop with participant
or improving their research efforts are especially
scientists and journal editors as speakers.
encouraged to apply.
The next workshop in the series will be
For more information about the conferences or
held in Washington, DC, February 5–6, 2009.
guidelines for proposal preparation and submis-
Announcements and application/registration infor-
sion, visit
www.cbmsweb.org or contact CBMS,
mation will be available at
www.niss.org. Space will
1529 Eighteenth Street, NW, Washington, DC
be limited, and pre-registration is required. n
20036; (202) 293-1170;
rosier@georgetown.edu;
lkolbe@maa.org. n
JANUARy 2009 AMsTAT NeWs 7
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 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80