iiinova — where your digital self keeps evolving

Jess Graves @jessgraves.bsky.social · 25/02/2026

Lmao at python being a dude vaping in a coffee shop

040

Reposted by Jess Graves

Darren Dahly @statsepi.bsky.social · 25/02/2026

I tried to tell y'all.

69823

Reposted by Jess Graves

Mid terms are November 3rd 2026. Go register voters. @usrbinr.bsky.social · 18/02/2026

#texas fam -early voting is here! Reach out to your network -remind them on voting Tomorrow is my birthday and to celebrate, I will of course go vote! @akjackson.bsky.social @libbyheeren.bsky.social @frankiethull.bsky.social @simontrose.bsky.social @jxmartinez.bsky.social @jessgraves.bsky.social

391

Jess Graves @jessgraves.bsky.social · 23/01/2026

Hi Bluesky! It’s been a while! We’re growing the Stats team at Loyal! We’re looking for a statistician with experience in observational and late stage interventional clinical trials in human or vet med. If that is you or anyone you know please apply! job-boards.greenhouse.io/loyal36/jobs...

job-boards.greenhouse.io

Statistician, Research

Remote - US

072

Reposted by Jess Graves

David Aerne @meodai.bsky.social · 23/11/2025

If you’re still hunting for color tools, I’m working on a more user-friendly version of meodai.github.io/poline/ keeping you huedrated

461910389

Reposted by Jess Graves

Neil Renic @ncrenic.bsky.social · 18/11/2025

Methodology

4467931330

Reposted by Jess Graves

Jorge 🐀 @jxmartinez.bsky.social · 18/09/2025

Hooray! See y'all next year in my hometown! 🐎 #positconf #rstats #htx

1102

Reposted by Jess Graves

Julia M. Rohrer @dingdingpeng.the100.ci · 17/09/2025

You're very welcome @vincentab.bsky.social P.S. Check out our preprint on an alternative to staring at coefficients: j-rohrer.github.io/marginal-psy...

Manipulated theatrical release poster of "The men who stare at goats" which now reads "the men who stare at coefficients"

Top shows the profiles of George Clooney, Jeff Bridges, Ewan McGregor, Kevin Spacey and a goat.

Below the text: the men who stare at coefficients with the silhouette of a man sitting in front of a computer screen, and the silhouette of a goat

28218

Reposted by Jess Graves

Vincent Arel-Bundock @vincentab.bsky.social · 17/09/2025

Whoa—my book is up for pre-order! 𝐌𝐨𝐝𝐞𝐥 𝐭𝐨 𝐌𝐞𝐚𝐧𝐢𝐧𝐠: 𝐇𝐨𝐰 𝐭𝐨 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭 𝐒𝐭𝐚𝐭 & 𝐌𝐋 𝐌𝐨𝐝𝐞𝐥𝐬 𝐢𝐧 #Rstats 𝐚𝐧𝐝 #PyData The book presents an ultra-simple and powerful workflow to make sense of ± any model you fit The web version will stay free forever and my proceeds go to charity. tinyurl.com/4fk56fc8

1130088

Reposted by Jess Graves

Julia M. Rohrer @dingdingpeng.the100.ci · 25/08/2025

Ever stared at a table of regression coefficients & wondered what you're doing with your life? Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social) Preprint: doi.org/10.31234/osf... Website: j-rohrer.github.io/marginal-psy...

Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities

Abstract
Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models).

Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve.

A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals).

Illustrated are
1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals
2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and
3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.

461001285

Jess Graves @jessgraves.bsky.social · 20/08/2025

Lil’ Muncher (official name lol) update: 1) LM abandoned his post at 50% consumption but 2) Found a friend, LM2 3) And many more 😵‍💫 Consumption rates have become exponential and sadly all (visible) Munch Bunchers had to be evicted.

$LM_{\inf} 🙃😵‍💫$

010

Jess Graves @jessgraves.bsky.social · 19/08/2025

Little muncher < 24 hrs later: 1) still on the same lead (! I was surprised by this!) 2) leaf consumption at 50%

282

Jess Graves @jessgraves.bsky.social · 18/08/2025

I’m supposed to hate this little cutie, because it will eat up my tomato plant but…. Come onnnnn look at it 🥹🥹🥹🥹

Carolina Sphinx caterpillar hanging upside down on a tomato leaf

381

Reposted by Jess Graves

Gavin Simpson @gsimpson.bsky.social · 18/08/2025

🚀 gratia 0.11.0 is out! Now has a paper in JOSS — please cite 📄 doi.org/10.21105/jos... Experimental parallel processing ⚡ New assemble() for building plots 🎨 Better support for complex families + new diagnostics 🧪 Lots of bug fixes + polish ✨ 👉 gavinsimpson.github.io/gratia/ #Rstats

gavinsimpson.github.io

An R package for working with generalized additive models

Graceful 'ggplot'-based graphics and utility functions for working with generalized additive models (GAMs) fitted using the 'mgcv' package.

318463

Reposted by Jess Graves

Aki Vehtari @avehtari.bsky.social · 11/08/2025

Reminder that all three books I've co-authored are freely available online for non-commercial use (and the fourth will be, too)

415350

Reposted by Jess Graves

Michael Friendly @datavisfriendly.bsky.social · 09/08/2025

#rstats So chuffed! I printed the first PDF copy of my book to see what it might look like in print! It will be printed in full color! Visualizing Multivariate Data and Models in R On the whole, looks good, but lots of tweaking to do. It weighs in at ~440 pgs., so perhaps some cutting needed.

Photo of me holding a printed copy of my book

Two -page spread showing graphs text and code

57615

Reposted by Jess Graves

Darakhshan Nehal @darakhshann.bsky.social · 08/08/2025

This plot has more than one *You had one job* kind of energy. ✨️ The prominent one, is using the same y-axis scale for both Median Home Price & Real Weekly Wages. Anyway, gently dropping my attempt to visualize the y-axis scaling mismatch: darakhshannehal.quarto.pub/scrollytelli... :) #dataviz

5334

Jess Graves @jessgraves.bsky.social · 07/08/2025

One my favorite resources!! I am working on a review of how paired t tests are a unique case of mixed models.

2111

Reposted by Jess Graves

Ben Collins @bencollins.bsky.social · 06/08/2025

AI filmmaking is peeing. It’s pooping. It’s throwing up. It’s a new kind of liquid coming out. It’s hated by the establishment. It’s what goes in the toilet. It’s wet. It’s what’s in the bathroom.

AI filmmaking and storytelling is punk rock. It’s hip hop. It’s counterculture. It’s a new type of creativity. It’s a new medium. It’s hated by the mainstream film and art establishment. It resists ideology. It ignores gate keeping. It’s uncomfortable. It’s scary. It’s viral. It’s accessible. It’s refreshing. It’s welcoming. It’s here.

579147982419

Reposted by Jess Graves

Rob Wesley @eastwes.bsky.social · 05/08/2025

“Do we like Damien? We like Damien, don’t we? It’s all for him, we do it all for him. We just want him to look at us. We treat him well, sometimes he’s not very nice to us, but it is for him, it’s really all for Damien.”

10739198

Reposted by Jess Graves

Audrey John MD PhD @odomjohnlab.bsky.social · 05/08/2025

To say that "the data show these vaccines fail" in regards to the mRNA plaform is unforgivable. For those of you that don't remember - this is the data from a SINGLE dose. In December 2020. So good I cried in grateful tears.

Kaplan Meier curve showing efficacy of mRNA vaccine against COVID-19

10545245

Jess Graves @jessgraves.bsky.social · 06/08/2025

Oh no. And, seems like they never adjusted for it or considered it a candidate covariate? 😢 This is a really great reminder that: 1. Blind pre-specification & testing “baseline imbalances” can really miss the mark. 2. Confounding due to differential loss to follow up is real and bad lol.

000

Jess Graves @jessgraves.bsky.social · 06/08/2025

Sometimes it's good to revisit the basics. Part 1 of a series on using the binomial distribution to interpret & power studies on rare events -- inspired by Martin Bland's write-up, "Detecting a single event". Spoiler: rare events are hard to find 😜 🔗: tinyurl.com/2hb9vh68 #rstats #stats101

2183

Reposted by Jess Graves

Danyal @danyals.bsky.social · 26/12/2024

Humans vs Ants attempting the “PIANO MOVERS PROBLEMS” Prof. Ofer Feinerman and his team at the Weizmann Institute of Science made this evolutionary competition that asks the question: Who will be better at maneuvering a large load through a maze?

0358

Jess Graves @jessgraves.bsky.social · 26/07/2025

Eye opening read on how tech companies view us as renters and not buyers.

181

Jess Graves @jessgraves.bsky.social · 23/07/2025

If this happened to me. Sheeeesh. Joy maxed out. Time to pack it up, friends. Couldn’t get better.

030

Reposted by Jess Graves

Michał Wypych @mwypych.bsky.social · 09/07/2025

#tidytuesday about colors from the xkcd color survey! Colors are always fun to work with. I looked at overlaps in descriptions of colors given by participants of the survey. code: github.com/mic-wypych/t... #rstats #dataviz #ggplot2

a plot showing overlaps in descriptions of colors (purple, pink, blue, brown and green) from the xkcd color survey

0221

Reposted by Jess Graves

Rodrigo Barreiro @rodrigo404.bsky.social · 08/07/2025

I can only imagine how "FUN" was to clean this #TidyTuesday dataset. This is my plot for the week. #R4ds #dataviz #ggplot2

4222

Jess Graves @jessgraves.bsky.social · 16/07/2025

*chef-kiss* so many times I've banged my head against my desk going "omg, nooo, not on all the facets!!!!!!"

181

Reposted by Jess Graves

Rajo @rajodm.bsky.social · 26/06/2025

#TidyTuesday week 25 📊 Exploring #measles incidence and laboratory confirmation rates in Africa (2024). Code: github.com/rajodm/TidyT... #dataviz #rstats #ggplot2

Bivariate choropleth map of Africa showing measles incidence rates and laboratory confirmation rates by country in 2024. Countries are colored using a blue-to-purple matrix where blue indicates low incidence with high lab confirmation (like Botswana), red indicates high incidence with low lab confirmation (like Liberia), and purple indicates high incidence with high lab confirmation (like Somalia). The map shows significant variation in both disease burden and diagnostic capacity across African countries, with 89,765 total measles cases reported.

2283

Jess Graves @jessgraves.bsky.social · 16/07/2025

Better late than never — here’s my #TidyTuesday submission from last week's data! I built a #shiny app with #plotly to explore the @xkcd.com color survey results in both 🌈 RGB and HSV space🌈. 🖥️ App: jessgraves.shinyapps.io/xkcd-color-s... 🌐 Personal site: jesslgraves.github.io/apps/2025-07...

1132

Jess Graves @jessgraves.bsky.social · 16/07/2025

An excellent old post I just discovered by @statsepi.bsky.social on the commonly held misconception that randomization is meant to “balance” factors. (My schooling 100% propagated this myth & taught us to always test baseline factors across groups & if p<0.05 then treat as confounding! 😬💀🤡)

open.substack.com

Out of balance

A perspective on covariate adjustment in randomized controlled trials in medicine.

1103

Reposted by Jess Graves

Darren Dahly @statsepi.bsky.social · 16/07/2025

One year on, it's probably time to check to see how the study i critique here has been cited. (ICYMI) statsepi.substack.com/p/one-simple...

statsepi.substack.com

One simple trick that statisticians hate

If you don't like the results, just ignore the control group

1124