What are people’s favorite statistics, methods, data science podcasts? Things like @quantitude.bsky.social, @casualinfer.bsky.social, in the interim, etc? #rstats #stasky #episky

See also, Cauchy? Which, bizarrely, is sometimes pronounced ‘Lorentz’.

Celebrating the draft FDA Bayesian guidance document with our perspective in @jama.com. Honored to co-author w/Jack Lee (MD Anderson), Lisa LaVange (past director of Office of Biostatistics FDA CDER&president of ASA),& my Bayesian inspiration Sir David Spiegelhalter jamanetwork.com/journals/jam...

Is worksmaxxing a thing? Like working at all possible times, even in unreasonable times, locations, etc. and also potentially to the detriment of relationships, hobbies, etc.

as far as exchangeability (Pr [Ya = 1|A= 1] = Pr [Ya = 1|A= 0]), the equality is before treatment/exposure, right? that's really the only thing that makes sense...but man, stating that explicitly would save a lot of confusion. i like that "what it" states this so clearly. #causalinferance

I’m in a Markov chain rabbit hole. Send help. #bayes

This is, of course, fabulous and should be followed. By my arch enemy is out there somewhere reading this and will now do the exact opposite.

This peak niche humor. 🔥

This is going to be a very long chain

Lousy smarch weather.

I fall in love with @gt-package.bsky.social every time I use it. I remember back in my early days when I’d manually make tables by looking at values in SAS outputs. Glad that is behind me. #rstats #statsky

Truncated count models should come with a bright, flashing warning light (and maybe some sort of horn) alerting users to the complexities of coefficient interpretation. Or maybe raw coefficient interpretation should just be outlawed? #rstats #statsky

Love it! And I’ve already simply attached this paper as my peer review on more than 1 manuscript. 😬

These captchas just keep getting harder #rstats

Another example of how high-impact journals seem to be click bait for scientists.

if i get asked one more time to join a "biostat made simple" speaker panel at a clinical medicine conference i am going to fuc!*ing lose my mind.

thank you, journal staff, for ensuring this paper has 5 key words (not 4!) and that they are listed after the abstract, but not (*oh, never*) on the same page as the introduction. as a peer reviewer, i would have been LOST without such safeguards.

The velomobile is my favorite mobile.

Everything I love and hold dear is slowly getting taken away from me.

In 2026, does anyone actually need/want/respond to unsolicited marketing emails? I get all sorts of stuff about basic science equipment. I find it hard to believe there is anyone out there just pounding their head against a wall wondering where they can get microscopy supplies.

I was today years old when I learned about prediction intervals in meta analysis. Seems great. Does the hive mind have thoughts, pro or con? introduction-to-meta-analysis.com/download/c17...

This is one of those conceptual knowledge bombs (delivered as a wonderful casual aside) that can make you question everything you thought you knew about statistics.

I tossed and turned all night thinking about the sample size calculation for this paper I am reviewing. Does this happen to other people?

What fresh hell is this?!?

I have a zero truncated count outcome. Continuous predictor of interest that has non-linear relationship outcome. But there is parity in some areas of the predictor space. So a penalized smooth à la mgcv. Packages that can do this? GlmmTMB. Gamlss. Any other others? Anyone have suggestions?

What fresh hell is this?

This is the content I’m here for! @f2harrell.bsky.social

So many great links in this thread.

I’m generally like a 2 or 3 dplyr verb in a single pipe kinda person. I just used 8 diff verbs and 14 pipes and I’m giddy. #rstats

At what stage of brownness are previously orange/red hot sauces considered no longer appropriate for consumption? Asking for a friend.

when doing data cleaning for a new project, sometimes i feel like sisyphus and most other times like odysseus. a new experience stemming from my current project is prometheus, where i'm chained to a rock and my liver gets pecked out every day from now until forever. #statsky

I’m at that point in my statistical life where I believe GAMs may be the answer to…many, many analytic problems.

I thought we were done with studies that use fMRI to support outlandish claims?

Grumpy old guy here: Apple updates are more and more resembling Microsoft updates—useless at best, more work for the same outcome at worst. Thanks Apple!

This brings me a lot of joy. I ❤️ GT packages. 🥰

Bias-variance tradeoff is one of those critically important statistical ideas that would be so much easier to grasp and discuss if it had a better name.

Something they never mention in parenting classes is how emotionally draining taking children mini-golfing can be. This is a huge oversight, imo.

In 2026, I resolve to need the phrase “I probably should not have eaten that” with substantially less regularity.

I’m in data cleaning hell and honestly considering asking an LLM to do it. I mean, not really considering it. But also not *not* considering it…

What in worst airline in the US and why is it @united.com?

I’m the kind of person who makes a Christmas pudding every year even though I am not British, and my family hates it.

Anyone with administrative experience in scientific publishing: Isn’t it financially burdensome for a journal to pay someone to look at submissions for formatting for all submissions? If 90% are rejected, that’s a lot of paper to look at for basically no benefit.

Apple updates are becoming nearly as annoying as Microsoft. Cosmetic ‘improvements’ and more clicks to do the same actions as the previous version. 🤬🤬🤬

nice ref and explanation of why "trending toward significance" is...not really a thing. www.bmj.com/content/348/...

nobody ever tries biting zombies to see if it turns them normal again and i think that's a mistake from a scientific perspective.

Unwillingness on the part of authors to provide CIs for main study results is: bizarre? Concerning? Some other adjective? What do other think?

Public service announcement: if you are writing a paper about sepsis, you don’t need to include ‘sepsis is a life threatening condition characterized by organ dysfunction in the setting of infection’. If we’re reading your paper on sepsis, we know what it is.

Does anyone know how to yeet the MIMIC database into the sun? Asking for a friend…

Can’t wait for all the junk, database/retrospective/registry papers comparing SOFA 2 to SOFA 1. jamanetwork.com/journals/jam...