Bayesian reanalysis can be a great way to assess a contested trial, by showing how strong a prior you need to nullify or inverse the results. I don't understand why they did not include a pessimistic prior here though (even as I see a sceptical one more realistic). #emimcc #cardiosky #cccsky #stats

The causal inference crowd needs a DAG signal

It’s not every day your one of your dearest friends becomes the president of a major medical specialty college. Congratulations Dr Tanya Selak aka @gonggasgirl.bsky.social President of the Australian and New Zealand College of Anaesthetists @anzca.bsky.social So proud of you #AnSky

Disclaimer: this is my first #quarto extension, I don't know what I'm doing That said, for who knows what reason I've always wanted a RevealJS feature where you can summon Wayne Knight to deliver his iconic "ah ah ah" line from Jurassic Park You're welcome (sound on) github.com/benharrap/ah...

Who said coding isn't fun? #Rstats

The Open Inference Lab just opened!🚀 A place for exploring statistical models, with a focus on making complex methods more transparent and easier to understand. First post: How to handle multiple binary outcomes in a Bayesian way bit.ly/4ujWL8a #statistics #bayesian #rstats

The "fraud is thankfully rare" era is clearly over. Jack's work (et al) is incredibly timely and important. If you review trials, please consider attending or otherwise learning more about INSPECT-SR.

🚀 New vignette: Uncover "Context Effects" in mixed models. Stop blending within- & between-person effects. Learn to demean variables and formally test state vs. trait differences side-by-side with the #RStats #easystats {modelbased}📦 easystats.github.io/modelbased/a...

Do you ever claim to be interested in the "association" between variables? This talk may be for you! @jeremylabrecque.bsky.social will explain when and why such associational language is not appropriate and why causal language should be used instead. Register here: ucl.zoom.us/meeting/regi...

The human circulatory system, before and after proper cable management.

If you're still dichotomising continuous variables, stop. Dichotomising your exposure &/or outcome wastes power. Dichotomising confounders introduces residual confounding. If a variable has non-linear effects, use splines! If you want 'clinically relevant' threshold effects, use marginalisation.

I think policies that support editors to desk reject more papers could free up capacity Dichotomise continuous variable - reject Stepwise variable selection - reject Table 2 fallacy - reject Etc If widely applied, this could drive up standards

"No, I am your father"

The Bayesian Workflow book is coming! statmodeling.stat.columbia.edu/2026/04/16/t...

Congratulations to @jdwilko.bsky.social for the citation of INSPECT-SR in testimony to the US House science oversight subcommittee and its mainstreaming of the scientific value of sleuthing.

many such cases

NCHDs look at me with two heads when I suggest they shouldn't litter their paper with the term "real world", mainly because their bosses train them to do exactly that.

Very interesting distributions from a RCT of antibiotic. Bimodal peaking at 0 and ~7, while also truncated at 0 What distribution would fit this best?

Added a statistical analysis tab to explore Bayesian partial pooling visualization (cc @rmcelreath.bsky.social). Added some model explanations too. Data viz heavily inspired by @benmoran.bsky.social's beautiful bayesfoRest package

I want to my son to grow up knowing that Han fired first.

THANK YOU FOR YOUR ATTENTION TO THIS MATTER

Every paper begins as a promise and ends as a compromise.

#rstats Periodic reminder: if you are writing articles / books w/ matrix, vector notation, my {matlib} 📦 has a whole suite of functions to make your life easier. Want a matrix X? --> latexMatrix() |> Eqn() Eqn() renders too in #RStudio Viewer See the vignette: friendly.github.io/matlib/artic...

#Bayes #stats @mc-stan.org folks, is this a great idea? Or a terrible idea?

If relevant, this paper lays out some alternative inverse-weighted and discrete-time approaches which can be implanted in standard software (nothing bayesian). tinyurl.com/4tb6emm7

In this paper we framed the waiting time to next event (initiation of next trt or death) as a competing risk model nested within a causal g-computation approach. doi.org/10.1093/bios... Similar data structure. Turns out you just need to model the sequence of cause-specific hazards.

I had somehow not noticed the 2.0 release of {lme4} last week, which includes functionality to specify structured covariance matrices. Nice! #rstats cran.r-project.org/web/packages...

Hivemind: I want to know the increase in survival time from repeated Tx visits over uneven times. Pts can be followed up repeatedly, and Tx can be given over multiple visits. I'm after time to each visit and time-to-outcome. What would you do? Weibull frailty model? This is in brms. #statsky #rstats

Are there any examples where it is defensible to combine observational and randomised data in a metaanalysis? #stats #metascience

New paper in press at Biometrics by PhD Candidate Esteban Fernández-Morales 1) Develops Bayesian spike & slab and horseshoe models for causal inference under spatial spillover 2) Analyzes Philly's 2017 beverage tax accounting for cross-border shopping arxiv.org/pdf/2501.08231

I can think of no surer way to make your spouse see the error of their ways than to point out how their current thinking is rife with confounders. Draw them a DAG while you're at it.

Proposing new rule: "Live your life in such a way that nobody will be forced to render parts of it as a 'Downfall' variant."

🚨 OMG! No words! #academicsky #idsky #statsky

With some help from Claude Code, I have the app I've always wanted: elicitcausal lets you design a causal graph with your theoretical priors & preregister it. Then after you complete a study, you can upload your graph and get estimates of causal learning. Link: causal.wilddata.solutions #rstats

I believe the Gen Z kids call this causalmaxxing 😎

By leveraging advances in #Bayesian statistical methods, this meta-analysis quantifies the role of publication bias in the field of #dexmedetomidine for #delirium prevention in #cardiac surgery patients

#stats Here's a nifty interactive demo of confidence intervals by Kristoffer Magnusson rpsychologist.com/d3/ci/

Revman and the idea of standardizing meta-analysis was brilliant in the 1990s. That is no longer the case.

Today, my pipes have pipes. Pipe-ception, if you will.

Why do I have to pretend that I'm going to print something in order to save it as a PDF. Why do I have to engage in a little ruse.

Very sadly Seshagiri Mallampati, the anesthesiologist who devised the Mallampati score, die two weeks ago. He only retired in 2017, 49 years after he began clinical practice. litfl.com/seshagiri-ra...

COULD EVERYONE PLEASE STOP USING RANDOM EFFECTS META-ANALYSIS WHEN COMBINING 3 OR 4 TRIALS? AND COULD REVIEWERS STOP DEMANDING IT?

Yes, we mention that here.https://pubmed.ncbi.nlm.nih.gov/40914655/. The post was really directed at the 99% of meta-analyses that use standard software and don't even include a statistician

Me? I'm just happy to be here #rstats

I'm so excited to announce the first release of my newest #Rstats package, {adrftools}! This package facilitates estimation, visualization, and testing for the causal effect of a continuous (i.e., non-discrete) treatment. 🧵 1/10 #statssky #episky #causalinference

I feel like that’s what we do already no?