Apr 1999

9:00 - 9:05    President’s Welcome
9:05 - 9:25     Jim Luhring "Advanced Placement Statistics at Cherry Creek High School"
9:25 - 9:45     Rinaldo Schinazi "Strategies to Control the Genital Herpes Epidemic"
9:45 - 10:05   Luis Tenorio "A Case Study from CMB Cosmology"
10:05 - 10:25 Doug Nychka"Spatial Statistics and Large, Non-stationary Datasets"
10:25 - 10:45 BREAK
10:45 - 12:15 Keynote Address: Trevor Hastie of Stanford University
                    "Additive Logistic Regression: a Statistical View of Boosting"
12:15 - 1:45   LUNCH
2:00 - 2:20     Claudia Tebaldi "Selecting among many linear models"
2:20 - 2:40     Tressa Kane "Cloud Seeding Effects on Rainfall Production"
2:40 - 3:00     Philippe Naveau "Study of the Higher Cumulants of Random Wavelets Coefficients of Non-Gaussian and Non-Linear Processes"
3:00 - 3:20     David Weitzenkamp "Cases per Predictor Variable in Logistic Regression: Simulation of an Already Published Study"
3:20 - 3:40     Tony Fagan "Probabilistic Environmental Risk Assessments"

Boosting is one of the most important recent developments in classification methodology. Boosting works by sequentially applying a classification algorithm to reweighted versions of the training data, and then taking a weighted majority vote of the sequence of classifiers thus produced. For many classification algorithms, this simple strategy results in dramatic improvements in performance. We show that this seemingly mysterious phenomenon can be understood in terms of well known statistical principles, namely additive modeling and maximum likelihood. In this talk we present boosting and our explanation, and then develop some modifications that improve its performance dramatically.

Colorado-Wyoming Chapter