Donna J. Brogan Lecture in Biostatistics

This lecture honors Donna J. Brogan, an outstanding former faculty member and chair in the Department of Biostatistics at the Rollins School of Public Health. The lecture is made possiblein large part by the generous support of Donna and her colleagues and friends. Donna has been Professor Emerita since her retirement from Emory in 2004.  

History of the Donna J. Brogan Lecture in Biostatistics

The Donna J. Brogan Lecture in Biostatistics was established in late 2004 by the Biostatistics Department of the Rollins School of Public Health of Emory University to honor the outstanding career of Dr. Donna Jean Brogan, a biostatistics/statistics faculty member at Emory for 34 years. Emory recognized Dr. Brogan's inspiring career with a gala retirement celebration in 2004. Her colleagues, friends and family members marked this occasion with gifts to support what would become the annual Donna J. Brogan Lecture in Biostatistics. These lectures, always in April, may be related to Dr. Brogan's research interests in sample surveys, breast cancer epidemiology and statistical education. Since the inception of the lectures in 2006, preeminent scholars and lecturers in biostatistics have visited Emory to deliver the lecture in honor of Dr. Brogan.

In 2010, Dr. Brogan made a significant contribution to establish an endowment fund that will provide funding continuity for the lecture. Her endowment, combined with generous gifts from colleagues and friends, makes possible one of only two named lectures at the Rollins School of Public Health. If you wish to contribute to the endowment fund for this lecture, click here. Please choose "Other" under Designations and enter the Donna J. Brogan Lecture in Biostatistics in the text box that appears.

2020 Donna J. Brogan Lecture

March 30, 2020 at 4:00 p.m., Reception following

Xiao-Li Meng
Xiao-Li Meng, Ph.D.
The Whipple V. N. Jones Professor of Statistics
Harvard University

Personalized Treatment: Sounds heavenly, but where on Earth did they find the right guinea pig for me?

Are you kidding me? Surely no one should take personalized literally. Fair enough, but then how unpersonalized is personalized? That is, how fuzzy should “me” become before there are enough qualified “me”s to serve as my guinea pigs? Wavelet-inspired Multi-resolution (MR) inference (Meng, 2014, COPSS 50th Anniversary Volume) allows us to theoretically frame such a question, where the primary resolution level defines the appropriate fuzziness - very much like identifying the best viewing resolution when taking a photo. Statistically, the search for the appropriate primary resolution level is a quest for a sensible bias-variance tradeoff: estimating more precisely a less relevant treatment effect verses estimating less precisely but a more relevant treatment effect for “me.” Unexpectedly, the MR framework reveals a world without the bias-variance trade-off, where the personal outcome is governed deterministically by potentially infinitely many personal attributes. This world without variance apparently prefers overfitting in the lens of statistical prediction and estimation, a discovery that might provide a clue to some of the puzzling success of deep learning and the like (Li and Meng, 2020). A personal and painful story, together with a Simpson’s paradox from comparing kidney stone treatments, will be used to regale the audience.

See the full announcement here.