[Cowystats] ASA Spring Meeting (April 18th) / JSM items

[Matt Pocernich]

### Chapter Spring Meeting - April 18th - Boulder
### JSM - Opportunity to get involved (part 1)
### JSM - Opportunity to get involved (students)
### JSM - Teachers workshop

With the spring meeting a little less than two weeks away, My
apologies in advanced for the multiple messages you will be receiving.
 Each will contain more details about the meeting.  With the JSM only
4 months away, we will be conveying more information about that event
as well.

### Spring Meeting - April 18th, 9 am to 3pm.  National Center for
Atmospheric Research - Boulder, CO

Once again, the spring meeting will be held at NCAR's Mesa Lab located
in the foothills just above Boulder.  For those of you who have never
visited the lab, this is a pretty spectacular location for a meeting.
For more information on the Mesa building and directions pleas see
http://eo.ucar.edu/visit/ .

The schedule for the spring meeting is slightly different than in
recent years.  We are ending the meeting slightly earlier than in
previous years.  This  allows people to get a jump on rush hour
traffic.  We have lengthened the lunch period.  There will be several
options for the extra time.  There will be a demonstration of the
VisLab (an advanced multi media room, with neat 3-D imagery).  One
could go for a walk/ hike in the foothills to the west of the Mesa
Lab.  (Once again, great weather is guaranteed.)  Finally, for those
interested, we will have a discussion about activities the chapter
might attempt or new ideas for the chapter.  Of course there will be a
chance for suggestions in the main meeting when chapter business is
discussed.  On the topic of chapter business, we need to elect people
to two positions - the president - elect and the treasurer.  If might
be interested in either position, please contact us.

Tentative Schedule

9 - 9:30 - Registration and refreshments
9:30 - 11:30 Presentations
11:30 - 1 pm. Lunch
12:30 - 1 Optional tour of NCAR's Vislab (http://www.vets.ucar.edu/Vislab/ )
1- 3 pm Presentation

*** Invited Speakers

+ Alicia Karspeck
NCAR Institute for Mathematics Applied to Geosciences

Title (To be announced)
Why Two Mammograms May Be Better Than One: the Science and the
Statistics

+ Deborah H. Glueck
Assistant Professor of Biometrics. Department of Preventive Medicine
and Biometrics.
University of Colorado Health Sciences Center. Denver CO

D.H. Glueck, M.M. Lamb, J.M. Lewin and K. E. Muller.

Glueck et al., 2007 compared the area under the ROC curve of
full-field digital mammography, screen-film mammography, and a
combined technique that allowed diagnosis if a finding was suspicious
on film, on digital, or on both.  We used data on paired full-field
and digital mammograms performed in 4,489 women (Lewin et al., 2002).
At the Bonferroni-corrected 0.025 alpha level, there was a significant
difference between both film and combined (difference = 0.07, p =
0.01) and digital vs. combined ROC curves (difference = 0.12, p =
0.001).
Using two mammograms, one film and one digital, significantly
increased the diagnostic accuracy.

In general, a combined test can have better diagnostic accuracy than
either component test alone, as occurred in the mammography example.
However, the combined test can also be worse.  Characterizing the
combined ROC curve analytically demonstrates that the correlations
between the two component tests for women with cancer, and for women
without cancer governs the gain in sensitivity and the loss in
specificity when combining test results.

+ Mary Meyers
Associate Professor of Statistics  Colorado State University

Title: Shape-Restricted Regression Splines in Action

Abstract:  Regression splines are smooth, flexible, and parsimonious
nonparametric function estimators.  They are known to be sensitive to
knot number and placement, but if assumptions such as monotonicity or
convexity may be imposed on the regression function, the
shape-restricted regression splines are robust to knot choices.
Monotone regression splines were introduced by Ramsay (1988), but were
limited to quadratic and lower order.  An algorithm for the cubic
monotone case is proposed, and the method is extended to convex
constraints and variants such as increasing-concave.    The restricted
versions have smaller squared error loss than the unrestricted
splines, although they have the same convergence rates.  The
relatively small degrees of freedom of the model and the insensitivity
of the fits to the knot choices allow for practical inference methods;
 the computational efficiency allows for back-fitting of additive
models.  Tests of constant versus increasing and linear versus convex
regression function, when implemented with shape-restricted regression
splines, have higher power than the standard version using ordinary
shape-restricted regression.


*** The list of student speakers and titles will be provided in the next note.


### JSM opportunity for students

Forwarded message; please contact Rick Peterson (information below)
for more information.

Each year at JSM, Monitors are recruited to assist with the Continuing
Education (CE) courses. In return for monitoring a course at JSM,
he/she
can attend another course of equal length for free. JSM registration
for course Monitors is not required. The CE courses are currently
listed on
the JSM Online Program found here:

http://www.amstat.org/meetings/jsm/2008/

I like to give notice of this opportunity to students in a statistics
program at a university in the city where JSM will be held. It is a
great way for students to attend for free a wonderful short course
taught by some of the best statistics presenters in the world. Since
you
are active with ASA, and a faculty member of the Department of
Statistics at the University of Colorado at Denver, I was hoping you
could distribute the attached Monitor announcement to your students.
If you have any questions, please let me know.

Rick Peterson

Education Programs Associate
American Statistical Association
Phone (703) 684-1221 ext. 1864
Fax (703) 684-3768
Email rick at amstat.org

####  JSM - Chairs for contributed sessions.

The JSM program is entirely organized by the national ASA organization
so basically, we at the local chapter level do not organize sessions,
speakers and staff.  Katerina Kechris from UCHSC wished to volunteer
to be a session chair.  After much persistence, she found that by
contacting the Section Chairs directly there are opportunities for
helping in the Biometric Section.   Presumably, these opportunities
exist in other Sections.
 To find a list of other  sections, see

http://www.amstat.org/meetings/jsm/2008/index.cfm?fuseaction=program

 From Katerina
------------------------------------------------------------------------
Subject: Statistics comes to Denver!

Dear Biostats folks,

As you know, JSM will be in Denver this summer. This would be a great
opportunity to get involved and advertise our program. The Biometrics
Program Committee Organizer is

Debashis Ghosh         ghoshd at psu.edu

I have already contacted him and he is eager to recruit more volunteers to
chair contributed sessions. The major responsibility for session chairs is
to introduce speakers and keep track of the time.

If you are interested in participating, please contact him asap with your
interests!

Katerina

### Teachers Workshop at JSM

Thanks to everyone who responded to my last note.  I haven't checked
with the workshop organizer, but with the exception of the K-4 age
group.


The following is a note from Jerry Moreno who is organizing the K-4
Session.  If you know of any teachers who might meet his needs, please
let him know.

******** From Jerry
Katharine Halvorsen asked me organize the MWM k-4 program. I have two
statisticians who have worked with elementary school teachers lined
up. I would like to have an elementary school teacher from the Denver
area who has expertise in data analysis. Do you have any suggestions?
I would want her or him to present classroom-proven activities for
about 75 minutes. Any suggestions you can make would be greatly
appreciated.

By the way, do you know Stirling Hilton? I was thinking about asking
him to do a session if I can't find an elementary school teacher.
Stirling is at BYU.

Thanks.
Jerry

Jerry Moreno
Dept. of Mathematics and Computer Sci.
John Carroll University
University Hts. OH 44118
moreno at jcu.edu
One this topic, one of the organizerswea looking for Jerry Moreno

More information on the Teacher's workshop can be found at
http://www.amstat.org/education/mwm/index.cfm?fuseaction=main

### Archive of chapter notes

As always, an archive of chapter notes can be found at

http://mailman.ucar.edu/pipermail/cowystats/