Sensitivity analyses play an important role in the reporting of randomized trials. But it's hard to do them well and their role and purpose is often misunderstood. Debbie Cheng and I address some of these issues in our Perspectives essay in NEJM nejm.org/doi/full/10.10…

Our Division is hosting its inaugural yearly Biostatistics Symposium, and this year the topic is Causal Inference! We have an exciting lineup of speakers listed below. If you are in the NYC area, please join us! Link to register in the QR below.

PSA - the main ideas behind “causal ML” and “double machine learning” go back at least 40 years Here is an estimator from a 1982 textbook that today would be called double machine learning or something similar

Thanks to Hamish Fraser for a great CCMB Seminar this week! It was great learning about the uses and limitations of diagnostic apps and large language models in helping patients diagnose and triage urgent and emergency conditions. Next seminar: 10/9 with USC's Adam MacLean

Walz: Matthew 25:40 talks about "To the least among you, you do unto me.” Let us keep our dignity about how we treat people.

21.3 million people are enrolled in the ACA marketplace this year, an all-time record, as Governor Walz points out. Nearly 50 million Americans have been covered by marketplace plans in the past 10 years. hhs.gov/about/news/202…

The media will say Vance won the debate. And in terms of performance, smoothness, sure, he did. But the only question that mattered tonight was Walz's to Vance: did Trump lose the election? Vance's refusal to answer was a reminder of his extremism and unfitness for office.

Walz is absolutely nailing the key point here: Vance would break his oath of office on Trump's behalf and place Trump above the law and the Constitution. Vance CONFIRMED THIS HIMSELF. This is what he actually meant when he confirmed that he would have done what Pence would not.

Thanks Benjy! Hard to think of a better panel to help scope out the future of biostatistics in the age of AI: Elizabeth Stuart Xihong Lin Kiros Berhane Rebecca Hubbard Wonderful to celebrate the contributions of so many people to the growth of Brown Biostatistics over the past 30 years

How can we know if AI is improving patient outcomes? With emerging technology the stakes can be high. Randomized trials are challenging. But done properly, they yield highest quality evidence. We Need More Randomized Clinical Trials of AI | NEJM AI ai.nejm.org/doi/full/10.10…

Fernando Valenzuela was absolutely electric ... and one of the true "good guys" of professional sports. He was an icon in LA and I know he will be missed by many. Fernando Valenzuela, Pitcher Whose Screwballs Eluded Batters, Dies at 63 nytimes.com/2024/10/23/spo…

Last Friday we celebrated 30 years of biostatistics at Brown with a symposium featuring fantastic talks by faculty from Brown and elsewhere. We've come a long way since 1994! It's a genuine privilege to be part of this remarkable academic community. sph.brown.edu/news/2024-10-2…

Reminder: Canceling your The Washington Post subscription is penalizing the journalists who provide the reliable, trustworthy reporting we all value. If Post goes under, it hurts us and its journalists. Not the owner. Don't cancel. If you have canceled, consider reinstating.

the most troubling part of all this is that people see him clearly for who he is and still vote for him. yes i've heard voters explain their reasons and i've read all the expert analyses. i don't need to hear it again. on a basic human level, i'll just never understand it.

Providence RI

Great meeting earlier today to share information and hear about progress being made by Brown University Legorreta Cancer Center at Brown University 2024 ACS-IRG Awardees Drs. Deepraj Ghosh, Ying Ma, and Theresa Raimondo #LegorretaCancerCenter shiyoko Robert W. Sobol Michelle R Dawson Benedito A. Carneiro, MD, MS Liang Cheng, MD

Check out our new paper developing Bayesian causal inference methods for recurrent event outcomes! We handle several complexities such as censoring, terminal events, and treatment timing misalignment. Best part: the Bayesian models are all implementable in Stan (Stan).

"... some of the angriest, most resentful people in America right now — people who seem very likely to have a lot of influence with the incoming Trump administration — are billionaires who don’t feel sufficiently admired." nytimes.com/2024/12/09/opi…

PEPFAR is one of the most successful global health programs ever. It provides HIV treatment for over 20 million people. And now it faces a funding delay of up to 6 months. Without access to treatment, HIV can rebound in less than a month. This is self-defeating stupidity.

A fabulous Katherine Eban piece When you use medicines like eye drops, you assume it won't blind you because it's contaminated The guy whose job it was to make sure those eye drops are safe just got fired Not how you make America healthy again vanityfair.com/news/story/the…