Tell me something you do when you code that other people would tell you that you shouldn't do. Tell me the rules you break! I'll go first: I work in untitled files in the wrong project directories all the time. Like, all the time. Yes, I do tend to lose things 😂 #databs #rstats #python

For the scientists out there, please download anything you may need from ERA Commons before Oct 1. If there is a shutdown, it will go dark. SROs and POs will likely not respond to your emails, also, and study sections will not meet. 2/2

Here is a plot in terms of PROJECTS rather than dollars. I am using projects rather than awards so that projects that received supplements do not get double-counted. While the FY25 curve is improving, it seems that the number of funded projects will drop by 3000-4000 compared with FY24.

For our #flowcytometry peeps, would you like to have a single fix/perm protocol that is optimised for everything? One that preserves fluorophores while allowing simultaneous TF and cytokine staining? How about 100-fold cheaper? You got it: currentprotocols.onlinelibrary.wiley.com/doi/10.1002/...

I got sucked into a great conversation and missed a talk I was excited for.... but luckily, @clauswilke.com puts all his work online in the most clean, organized, and helpful ways!!! 🥰 I've been using Claus's course sites as my templates for years, he is the best. 💙 clauswilke.com/PositConf2025/

Bats 🦇 aren’t even on the list!

New NIH Notice about International Collaborations grants.nih.gov/grants/guide... 1/3

Damn. This is very, very bad. It is hard to overstate how bad this would be. It's pure anti-vax-ism. Parents would have to bring their kids to the doctor 3-5 times more to get vaccines because of Prasad's junk science?

Okay, so you've crunched your numbers and got some awesome statistical models? Sometimes, just knowing "X predicts Y" isn't enough to really get to the juicy bits. That's where the cool post-hoc stuff comes in – think estimated marginal means, contrasts, pairwise comparisons, or #marginaleffects.

Underrepresented minority faculty in the USA face a double standard in promotion and tenure decisions

Thanks for sharing this with me @botanicalbecks.bsky.social. Very insightful!

Or we could just start using {conflicted}. conflicted.r-lib.org/reference/co...

Per multiple sources, the EPA will cease recognizing employee unions tonight, removing their ability to collectively bargain.

This is important work and it is great to see it done carefully

Scanning the editor summaries this seems to confirm “this is how science works” and not “omg crisis”.

Hadley Wickham (@hadley.nz) is a developer and teacher whose impact on the R ecosystem is immense. He is Chief scientist at @posit.co where he leads the Tidyverse team. His keynote "I wrote this talk with an LLM" explores how AI can help rather than replace data scientists. user2025.r-project.org

I wish there was a textbook that took this approach in ecology/biology.

Federal agencies hiding out in a bunker

This RFI includes a request for input on the notion of peer review compensation. In case you were not motivated to reply on the publishing costs, this is another issue of importance to some. grants.nih.gov/grants/guide...

Some journals are claiming that you need to pay big $$ for gold open access to comply with NIH's new public access policy. FYI that is total bs. You can comply by depositing the Accepted Manuscript into PubMed Central on the Date of Publication without embargo. Pass it on.

CRITICALLY, agencies SHOULD NOT be proceeding as if a rescission package will pass. Obligate all the funds until the minute a rescission package passes. Stop only then.

Thank you, AAUP. It is good that some institutions are speaking up for science and academia, even as university presidents and boards are too naive to politics and too cowardly to fight.

“With these considerations, we expect to fund through the 4th percentile.” There it is, in black and white, the destruction of cancer research in the US.

This morning, NASA released the #VoyagerDeclaration. This afternoon, NIH #BethesdaDeclaration signers met w/ Jay Bhattacharya. Earlier, EPA staff were terminated for their act of resistance. I made this in solidarity. @altnih4science.bsky.social @altnasa.bsky.social @alt-epa-workers.bsky.social

I'm back home with my dad and have thoughts about being an Indigenous scientist and academic. I'm writing this in real time so it might get disrupted and will have typos. I am fairly successful by academic standards. I have a tenure track job, wrote papers, have grant funding, mentor students.

of Note: "Research Experiences for Undergraduates [REU].—The Com- mittee was dismayed to hear about the cancellation of numerous REU programs during 2025...and provides not less fiscal year 2024 enacted level.

🧪 For those following indirect rates (not normally an issue with so much drama!): Senate bill, out today, seeks to block the admin from making abrupt changes to indirect rates at NSF, NASA, and NOAA: www.appropriations.senate.gov/imo/media/do...

This is so cool. A new R implementation of our 2003 work on the role of evolution in emerging infectious diseases makes it easy to explore how beneficial mutations can drive the emergence of novel zoonotic disease.

IMPORTANT IMPORTANT IMPORTANT IMPORTANT Please watch the workshop video and COMMENT by 5:00 Monday 7/14 This is the source of the "no more model organism only grants in NIH-funded research" decree.

Chronicle of Higher Education article about new indirect cost proposals. www.chronicle.com/article/high... 1/n

This is how you can use a global style in #tidyplots 0.3.1 🌍 #rstats #dataviz #phd

BREAKING: The Supreme Court, via the shadow docket, has greenlighted the DOGE mass firings. From us at NIH: The Supreme Court is an arm of Trump and Republican Party. It is not a court, but a political body. And it must be disempowered if we want functional science in the US. 🧪

Really infuriating stuff. There's no place for AI in the classroom. AFT needs to follow the lead of @aaup.org and understand that these technologies are part of the increasing move to corporatize the classroom.

{tinytable} is a dead simple, ultra-flexible, and dependency-free #Rstats 📦 to turn data frames into beautiful tables: html, word, pdf, latex, typst, markdown, etc. v0.10.0 has cool new features and important bug fixes. Check out the detailed tutorials at: vincentarelbundock.github.io/tinytable/

The same is true for NIH funding. Congress told NIH what to spend on science and to do it with peer review and consider diversity. It is NOT UP TO Trump and Vought to cancel grants. It is NOT UP TO them to fire public servants administering the agency as a backdoor way to cut funding. 1/

NEW! 🎉 We need wildlife disease surveillance to predict epidemics, but data sharing is rare - we found that only 2-3% of studies share raw data. So, we spent three years developing a data standard and R package to help get wildlife disease data into FAIR repositories. www.nature.com/articles/s41...

Well, this is impressive (stem cell treatment reverses insulin needs for some type I diabetics) but ... they have to take immunosuppresive drugs possibly forever at this point, so this could end up being worse than diabetes for many people. www.nytimes.com/2025/06/20/h...

I've been fortunate to have a network of data freelancers that have been a huge support in my own work. I've started a list of some of these consultants (in academia, nonprofit, public sector, and industry). If you are looking for help, check out this list! #databs docs.google.com/spreadsheets...

Thanks to the ACLU for taking on this fight. A great day for public health and a great day for fairness and justice.

AMFAR has published a report on how the foreign aid freeze affects PEPFAR, which actually still hasn't resumed. They estimate that hundreds of thousands of people lose access to HIV antivirals and 1500 babies are expected to contract HIV — *each day* 🧵

🚨🚨Important: Why did the Trump admin do a Friday night news dump for the NSF and NIH Trump budgets? Because they are AFRAID. 😟 They know that killing science and disease research is a political Achilles heel for them. We scientists have not yet used our strength. We must. 🧪

Proud to sign on this this open letter. Join me.... www.standupforscience.net/open-letter-...

Another thing for #Rstats users: The new-ish Air code formatter for R is cross-IDE (available for RStudio, VSCode, Positron etc.) - so you'll end up with consistently formatted code no matter the IDEs used in a project. And it's Rust-based so performance is great www.tidyverse.org/blog/2025/02...

The Copilot Delusion buff.ly/99QsTEM <- the story is that one thing LLMs are good at is helping programmers. An experienced programmer carefully explains, in detail, why this is not true.

My latest in @plosbiology.org journals.plos.org/plosbiology/...

I'll be leading a workshop with Justin Landis at useR! in Durham on August 8. It will be a gentle introduction to how we model biological data using tidy data principles user2025.r-project.org

And practical tip: This new response in the FAQ indicates that NSF will try to use 15% if someone proposed that, regardless of what the courts decide. The take-away message for institutions: use your regular rate. Or else we'll take you up on 15%. www.nsf.gov/updates-on-p...

🧪 Basic science boosts the economy: "The proposed dismantling of NSF [and NIH] raises an urgent question: do these cuts actually save money or merely delay spending until the bill gets larger? The answer is clear: these cuts will cost the economy billions."

Thanks to everybody who chimed in! I arrived at the conclusion that (1) there's a lot of interesting stuff about interactions and (2) the figure I was looking for does not exist. So, I made it myself! Here's a simple illustration of how to control for confounding in interactions:>

1/ I’ve used Unix daily for years. Then I learned !$. And suddenly, it felt like a secret door had opened. Let me show you the trick.