Colloquium Victor M. Panaretos: Sums of Squares from Pythagoras to Hilbert via Fisher

By Victor M. Panaretos, Institute of Mathematics, EPFL, Switzerland

For one hundred years, the analysis of variance has been at the core of statistical inference. Though Fisher first distilled the notion circa 1920, its roots go much deeper in time, and ultimately lie in some of the most elemental concepts of geometry. This, in turn, lends it considerable versatility as statisticians grapple with data that are increasingly complex in their mathematical description. I will try to illustrate that, particularly when the data are infinite dimensional, the analysis of variance can help statisticians elicit order out of chaos, apparently promising to remain at the core of statistics for another hundred years.

Short CV:

Victor M. Panaretos is Professor of Mathematical Statistics and Director of the Mathematics Institute at the EPFL. He received his PhD in 2007 from UC Berkeley, advised by David Brillinger. Upon graduation he was appointed as Assistant Professor at the EPFL, where he rose the ranks to Full Professor. He received the Erich Lehmann Award for an Outstanding PhD (UC Berkeley, 2007), an ERC Starting Grant Award (2011) and was named “One of 40 extraordinary scientists under 40” by the World Economic Forum (2014). He is an Elected Member of the ISI (2008) and a Fellow of the IMS (2019). He was the Bernoulli Society Forum Lecturer in the 2019 EMS, and will be a plenary speaker at the XVI Latin American Congress in Probability and Mathematical Statistic (CLAPEM). He is an Associate Editor for Biometrika, and the Journal of the American Statistical Association (Theory and Methods), and previously for the Annals of Statistics, Annals of Applied Statistics, and Electronic Journal of Statistics. He has served the discipline from various posts, most notably currently being President-Elect of the Bernoulli Society.

REGISTRATION: