Opinion | The Old Man Dreaming Up Wars for Young Men to Fight Any deal with Iran would probably be a bad one. But sending ground troops to seize Iranian territory would be an even worse choice.

In @nytopinion.nytimes.com

“For all the uncertainties, one truth I feel deeply from having seen war up close: Old men should not fix their messes by dispatching young people to die in unnecessary wars,” our columnist @nickkristof.bsky.social writes.

The ending to Bad Bunny's halftime show:

"The only thing more powerful than hate is love"
"Together, we are America"

Timeline: How the Shooting of Alex Jeffrey Pretti Unfolded (Gift Article) A moment-by-moment analysis of video from the scene shows that Mr. Pretti was already restrained when fatal shots were fired, which appears to contradict the federal government’s account of the event.

The New York Times has published a timeline of events based on videos from the scene
www.nytimes.com/interactive/...

IMO, someone should compile a clear video of the critical moments of this interaction, viewed from multiple angles: Pretti was filming from afar, he was approached by agents, he helped a woman who was pushed to the ground, he was attacked in the face with pepper spray, and then he was shot.

The Washington Post published a clear video of federal agents removing Alex Pretti's handgun moments before he was fatally shot. There's nothing in the video to suggest Pretti even reached for his weapon.

wapo.st/49Zqv1L

Quantification method affects replicability of eQTL analysis, colocalization, and TWAS eQTL mapping and TWAS are widely used to contextualize GWAS, yet the impact of RNA-seq processing choices remains unexplored. We find that RNA-seq quantification method and transcriptomic reference su...

In this preprint, led by @nolancole.bsky.social (PhD student in Biostats at UW) and William (Undergrad! in BioSciences at Rice) we demonstrate how annotation choice and quantification method have significant downstream impacts on colocalization and TWAS results www.biorxiv.org/content/10.1...

More great work from Lars at UW!

Thrilled to share our new paper! We introduce a generalized autoDML framework for smooth functionals in general M-estimation problems, significantly broadening the scope of problems where automatic debiasing can be applied!

Lars van der Laan, David Hubbard, Allen Tran, Nathan Kallus, Aur\'elien Bibaut
Automatic Double Reinforcement Learning in Semiparametric Markov Decision Processes with Applications to Long-Term Causal Inference
https://arxiv.org/abs/2501.06926