George Mason University
AES/CCS/SCS/Statistics Colloquium Series
Seminar Announcement


Some Statistical Analyses: Designs to Data Mining

William B. Smith

Executive Director
American Statistical Association


Innovation Hall, Room 136, Fairfax Campus
George Mason University, 4400 University Drive, Fairfax, VA 22030

Time: 10:30 a.m. Refreshments, 10:45 a.m. Colloquium Talk
Date: April 28, 2006



ABSTRACT

With the advent of modern computers, inexpensive memory and automatic measurement devices, the volume (n) of multidimensional (p) data available for ‘analysis’ has increased beyond belief. The speaker will discuss examples appropriate for various combinations of n and p. Traditional statistical methods focused on problems assuming large or small n with a small p. Small n and large p problems (commonly called ‘the curse of dimensionality’) have been attacked, also. However, given the massive information now available, the community must address ‘large n, any p’ problems. The speaker plans simply to talk through several consulting examples and then open the discussion on where the statistics profession should be going relative to data mining.