Past Meetings

Speaker:    Vladimir Cherkassky, - Professor, Electrical and

   Computer Engineering, University of Minnesota

Date/Time:   Wednesday, May 19, 2010 / 5:30 - 8:30 p.m.

There was good attendance at the Chapter meeting for Professor Cherkassky's talk on predictive learning. He gave an excellent overview of predictive learning methods and their role in scientific discovery. There was considerable discussion about the extent to whick knowledge discovery can be obtained from data mining methods versus more classical scientific methods. Support Vector Machines (SVM) were covered in detail with several case studies in biomedical applications. Useful information about the application of SVM was provided including software resources.

Chapter President Arkady Shemyakin discussed chapter business and the election of chapter officers. More details will provided here as they become available.

Chapter members enjoying dinner before the talk.

Chapter President Arkady Shemyakin (left) talking with a chapter member.

-------------------------------------------------------------------------------------------------------------------------------------------------------------------

December 9, 2009 Chapter Meeting

Title:    Comparing Two Multivariate Normal Means
Speaker:    R. Dennis Cook - Professor, School of Statistics, University of Minnesota
Date/Time: Wednesday, December 9, 2009 / 5:30 - 8:30 p.m.
Location:    University of Minnesota
   President’s Room CMU-332
   Coffman Memorial Union
   300 Washington Avenue SE, Minneapolis, MN 55455

Meeting schedule:
5:30-6:30 p.m. Social and refreshments
6:30-7:30 p.m. Talk
7:30-8:30 p.m. Chapter business

If you plan to attend, please send an email RSVP by 12/7/09 to our treasurer Stan Lipovetsky: stan.lipovetsky@gfk.com

Abstract: We will revisit the classical problem of comparing the means of two multivariate normal populations with equal dispersions. It will be argued that is some settings it is possible to estimate the mean difference with substantially smaller variation than that of the usual difference in sample means, without introducing worrisome bias.

The reduction in variation can be massive, equivalent to increasing the sample size for the usual difference in sample means by a factor of 1,000 or more. The idea is based on a novel mechanism -- called an envelope -- for linking the mean difference with the dispersion matrix. Similar envelope constructions can be used in many different multivariate problems and some of these will be described briefly. The presentation will mostly appeal to intuition, with only essential details.

About the speaker: Dennis Cook is Full Professor, School of Statistics, University of Minnesota. He received his BS degree in Mathematics from Northern Montana College, and MS and PhD degrees in Statistics from Kansas State University. He served a ten-year term as Chair of the Department of Applied Statistics, and a three-year term as Director of the Statistical Center, both at the University of Minnesota. His research areas include dimension reduction, linear and nonlinear regression, experimental design, statistical diagnostics, statistical graphics and population genetics. He is author or co-author of two text books – An Introduction to Regression Graphics, and Applied Regression Including Computing and Graphics – and two research monographs, Influence and Residuals in Regression, and Regression Graphics: Ideas for Studying Regression through Graphics. Background on his graphics work can be found at http://www.stat.umn.edu/RegGraph/.

He has served as Associate editor of the Journal of the American Statistical Association, The Journal of Quality Technology, Biometrika, Journal of the Royal Statistical Society and Statistica Sinica. He is a three-time recipient of the Jack Youden Prize for Best Expository Paper in Technometrics as well as the Frank Wilcoxon Award for Best Technical Paper. He received the 2005 COPSS Fisher Lecture and Award. He is a Fellow of the ASA and IMS, and an elected member of the ISI.

Directions to Coffman Memorial Union and parking instructions can be found on the university web site: http://www1.umn.edu/twincities/maps/CMU/index.html

Parking: Parking is available at the East River Road Garage 3. For a map and directions go to: http://www1.umn.edu/twincities/maps/CMU/index.html

For information about joining the American Statistical Association, go to: http://www.amstat.org/membership/becomeamember.cfm
For information about member benefits, see the ASA Membership Guide: http://www.amstat.org/membership/pdfs/memberguide.pdf

Food and beverages will be available free of charge for Twin Cities Chapter members---for non-members there will be a charge of $3 for students and $10 for non-students. These fees will also allow you to become a Chapter member!

Meeting announcements will be emailed to Chapter members who have informed the ASA of their email address.

Older Meetings

Edit