It is utterly catastrophic that RFK Jr. plans to end CDC recommendations for most childhood vaccines. It’s a betrayal of science, ethics, compassion, and the people of the United States. And it was also a specific goal of Project 2025 (page 254).

As an editor I often see authors fall into a trap of stressing some fancy statistical technique for estimating causal effects. Often neglected are the necessary assumptions to map the data to the estimand. @pausalz.bsky.social and I wrote about it here www.bmj.com/content/391/... #EpiSky

Big new blogpost! My guide to data visualization, which includes a very long table of contents, tons of charts, and more. --> Why data visualization matters and how to make charts more effective, clear, transparent, and sometimes, beautiful. www.scientificdiscovery.dev/p/salonis-gu...

Currently dorking out over this graph about child mortality with my brother. Just mind boggling to take in.

Rearranging variables can make this clearer. In plot below, it's relatively easy to see that total effect needs no adjustment, and that direct effect from A to Y needs to block the indirect path that traverses D and C. D is a collider, and C the child of the collider, hence adjustment on B is needed

”by = x” generates predictions for the data “as is“ and then averages them for each level of x (eg average of predictions for the men in the data) “variable = x” generates predictions for counterfactual datasets in which x is set to different levels (eg average prediction “if everybody was a man”)

New on CRAN: UComp (5.1.5). View at https://CRAN.R-project.org/package=UComp

Confidence interval discussion time! The perfect opportunity to repost this blog post answering the question you haven’t dared to ask: www.the100.ci/2024/12/05/w...

With a link that works for those not at BU!: bit.ly/43lEIn2

We wrote an article explaining why you shouldn't put several variables into a regression model and report which are statistically significant - even as exploratory research. bmjmedicine.bmj.com/content/4/1/.... How did we do?

We built the openESM database: ▶️60 openly available experience sampling datasets (16K+ participants, 740K+ obs.) in one place ▶️Harmonized (meta-)data, fully open-source software ▶️Filter & search all data, simply download via R/Python Find out more: 🌐 openesmdata.org 📝 doi.org/10.31234/osf...

Just because an LLM can produce a report with various figures & charts doesn't mean it is good at statistics. Because good statistics is not about producing code. It's about deep knowledge of study design & conduct. In my opinion, 95% of all data science problems come from poor questions & design.

Autism has gone up by a factor of five since 2000 but acetominophen use during pregnancy has been going down. Sorry but the math just ain’t mathing.

Excited to share a new article with Delaney Glass & @lucia-petito.bsky.social in the American Journal of Human Biology! 🧬 We introduce a roadmap for causal inference with observational data in human biology & biocultural anthropology. (1/4)

2️⃣ weeks! 2025 Methods Series @ki.se continues. "Promoting the use of causal inference methods in applied health research by integrating causal reasoning into academic curricula: barriers and solutions." 📆 Oct 7, 2025 ⏰ 15.00 CEST/9.00 ET 📍 Online Register 👇 stats.sender.net/forms/e7JD1d...

🧵 I’m a public health researcher who wants to build bridges This podcast ep with #MAHA folks from May has been taking up brain space all summer the convo was illuminating & discouraging @meganranney.bsky.social @kkjetelina.bsky.social podcasts.apple.com/us/podcast/w...

I'm going to do a quick #MEstimatorMonday (36/52) to show how the pooled logit EE can be used to construct inverse probability of censoring weights (IPCW) This is based on the algorithm in my pre-print, but needs a few tweaks arxiv.org/abs/2504.13291

When using observational data for #causalinference, the choice isn’t between emulating or not emulating a #TargetTrial, but between reporting or not reporting the target trial that we are emulating. For those who prefer to be explicit about what they do, we have developed the TARGET Statement 👇

The TARGET reporting guidelines for target trial emulation studies have arrived! #EpiSky #CausalSky jamanetwork.com/journals/jam...

It’s crazy that America just like. Destroyed science. Just looked at its golden goose and went “wow should we kill this? And not for the gold, but just because we fucking hate this thing” And if you tell random people about it they go “no, that doesn’t seem true” and just refuse to believe you

NEW 🚨 The violence is the point. Elected Dems must call for widespread resignations (RFK, Bhattacharya, Prasad) in response to the CDC shooting. Public health must demand this of them, and the public must demand that of us. With @publichealthguy1.bsky.social in STAT: www.statnews.com/2025/08/15/c...

Just in case there was any doubt, ChatGPT 5.0 still makes up completely random citations that don't exist and should not be used for literature search.

A letter from myself and @jdwilko.bsky.social that expands on this a bit more. Thanks to Fertility and Sterility for the opportunity. doi.org/10.1016/j.fe...

a major argument in favor of LLMs is they will speed up scientific research, especially in human health. but when they are spending >10x the biomedical research burdget every year, it is very hard to argue that the money wouldn't be better spent simply paying for biomedical research.

SAVE THE DATE: The 2026 IEA European Congress of Epidemiology and 70th @socsocmed.bsky.social Annual Conference will take place in London, UK on 8th-11th September 2026! #EpiSky #EuroEpi2026

RFK Jr. has now officially stated that he will dismantle the United States Preventive ServicesTask Force (USPSTF). This is an independent body of expert scientists who volunteer their time to review data and provide guidance to Americans on important things like cancer screenings.

A nice recent article on why you should abandon hazard ratios. #statssky #episky

Less than a decade ago, reactions for adding, deleting, and swapping single atoms in complex organic molecules were almost unheard of. Now there’s a growing community of researchers working on them. cen.acs.org/synthesis/Sk... #chemsky 🧪

We're thrilled to share Associate Professor Mark Levin has been named a recipient of the 2025 National Brown Investigator Award. This award provides up to $2 million over five years and supports fundamental science discoveries in chemistry and physics. physicalsciences.uchicago.edu/news/article...

🎉Congrats to Mark Levin, Associate Professor of Chemistry, who received a 2025 National Brown Investigator Award! 🎉 https://physicalsciences.uchicago.edu/news/article/mark-levin-associate-professor-of-chemistry-receives-a-2025-national-brown-investigator-award/

Northwestern has not received any NIH funds since March. No written communication about why or what can be done. Thank you Ben Singer for raising awareness at #ATS2025

What is the best minimal-assumption method for estimating the relationship between continuous x and probabilty of survival to a fixed time t? New blog article: fharrell.com/post/kmove #Statistics #RStats #StatsSky

“It’s extremely alarming that grants that have been vetted by the scientific community and deemed important and impactful to understand the world are now being cancelled because of political ideology,” says @lkfazio.bsky.social. “This is direct censorship of scientific research.”