Dear Friends,
This is a reminder that our Sep webinar will be at 1pm Eastern Time TODAY, featuring Dr. Tim Hesterberg from Instacart. We hope to see you there!
Title: Covariate Adjustment, Intro to Resampling, and Surprises
Speakers: Dr. Tim Hesterberg, Instacart
Date and Time: Sep 30, 2026, 1:00 to 2:30 pm Eastern Time
Registration Link: ASA SLDS Webinar Registration Link
Abstract: Covariate adjustment is a relatively simple way to improve A/B test accuracy and velocity, and to reduce bias. Huh? Aren't randomized experiments unbiased? Well, yes and no - yes by the usual statistical definition, but no by a more common-sense definition. Furthermore, in practice there are some complications, particularly related to measuring how accurate the results are. Enter resampling (bootstrap, jackknife) - generally useful techniques for measuring accuracy. These bring their own surprises. Remember the old n >= 30 rule for using normal approximations? We'll see just how bad that is.
Presenter: Dr. Tim Hesterberg (http://www.timhesterberg.net) is a Staff Data Scientist at Instacart. He used to be a Senior Data Scientist at Google. That means old. He earlier attempted jobs at an electric utility, in academia, and in software; at least he can drive a forklift. He received his Ph.D. in Statistics from Stanford University, where he played a lot of volleyball, got his B.A. in Math from St. Olaf College, where he proved he can't sing, and claims he studied two years in Germany, but has nothing to show for it.
He wrote Mathematical Statistics with Resampling and R, Wiley with Laura Chihara of Carleton College, and got her to do most of the work. The first version wasn't good enough, so they tried again, and again. He exploited two college students and a high school teacher to write book chapters for teaching intro stats using resampling, then added David Moore as a co-author so people would think it was worth reading. He can't seem to stick to one thing; he's also written about streams and earthquakes, electric demand forecasting, web traffic, clinical trials, display ads, computer vision, and spiders walking around spaceships.
He was a high muckety-muck for Canadian Statistical Sciences Institute and the National Institute of Statistical Sciences until they got rid of him. He helped write the ASA Guidelines for Undergraduate Statistics Programs, so he could tell teachers how to teach. He was used as an example in "How to Give a Really Awful Presentation".
He runs or bikes to work. When he drives the accident rate in Seattle skyrockets. He broke his toe at a Math contest. He is a tree hugger, teaches kids to shoot rockets, make kerosene torches and set rafts on fire, and has herded cats - I mean chaperoned high school students - to set up computer labs in Guatemala, Ecuador, and Costa Rica.
------------------------------
Boxiang Wang
Associate Professor
Department of Statistics and Actuarial Science
University of Iowa
Iowa City, IA, United States
------------------------------