(Dr. Kobi Abayomi, who invites us to this talk, is one of our first graduates of the GT public policy undergraduate program; he went on to earn a doctorate in statistics at Columbia and joined the GT faculty last year.)
Statistics Seminar: 11.19.2009, 11:00-12:00 in Executive Classroom, ISYE Main Bldg:
Speaker: Professor Rand Wilcox, University of Southern California
Talk Title: HOW MANY DISCOVERIES ARE LOST BY IGNORING MODERN STATISTICAL METHODS? AN UPDATE WHEN COMPARING GROUPS AND STUDYING ASSOCIATIONS
Talk Abstract: The goal is to summarize some recent results when comparing groups and dealing with regression. The primary focus will be on results related to measuring effect size and comparing measures of association. Methods based on both Pearson’s correlation and robust measures of association will be described. The results on robust measures of association include situations where the strength of an association is based on a nonparametric regression estimator (LOESS) that provides a flexible approach to curvature. Other topics that will be briefly discussed include an extension of the shift function to a two-way design, results related to testing the fit of a particular quantile regression estimator, and a new approach to ANCOVA.
Rand Wilcox is a professor in the department of psychology at the University of Southern California who specializes in robust statistical methods and related issues. He is the author of eight books on statistics and over 280 journal articles. He founded and currently runs the interdisciplinary statistics group at the University of Southern California.
He currently serves as an associate editor for Psychometrika, Communications in Statistics–Theory and Methods, Communications in Statistics–Simulation and Computation, and Computational Statistics and Data Analysis. He is on the editorial board of several other journals and was recently elected a council member of the International Association of Statistical Computing.
Kobi Ako Abayomi
Georgia Institute of Technology
School of Industrial and Systems Engineering – Statistics Group