Jesse Onland @jdonland.bsky.social · 22/09/2026Posit is an LLM propaganda outlet that happens to maintain some #rstats packages. 140
Jesse Onland @jdonland.bsky.social · 22/09/2026Maybe I'm missing something but isn't the result here a bit obvious? If the cost of search effort doesn't depend on location and your prior is non-degenerate, you could always have picked a prior that was denser around the true target location and found it at less cost. arxiv.org/html/2311.18...arxiv.orgOn the true detection probability of the uniformly optimal search plan 000
Jesse Onland @jdonland.bsky.social · 16/09/2026Mercator's projection was very useful in its time: a straight line on the map corresponds to a path of constant bearing on the globe. When navigation was done with a compass and astrolabe, this was crucial. He didn't make Africa and Greenland look the same size just for fun! 1152
Jesse Onland @jdonland.bsky.social · 16/09/2026It's remarkable how quickly LLM token (slopbot store credit) usage efficiency has become the primary selling point of software packages. 010
Jesse Onland @jdonland.bsky.social · 16/09/2026Seeing Hadley suggest using LLMs to maintain the #TidyTuesday repo is a little depressing. It's an unpaid community project. If it's not worth doing by hand, why do it? Why not automate the whole thing, then? Let the bots make up datasets, maintain the repos, make the charts, and post about them. 281
Jesse Onland @jdonland.bsky.social · 10/09/2026300-character book review: "The Theory That Would Not Die" (2011) Brings its heroes and villains to life with charming short biographies, but mangles the statistical ideas. "Fisher considered a hypothesis significant if it was unlikely to have occurred by chance"? Hypotheses don't "occur" at all! 000
Reposted by Jesse Onland Minnesota Aquatic Invasive Species Research Center @maisrc.bsky.social · 19/08/2026MAISRC’s Quantitative Ecologist Alex Bajcz has created ggplotplus, an accessibility component for ggplot2, to produce graphs for posters, presentations, papers, and exploration. Especially helpful for ggplot2 users with limited time, energy, or experience. github.com/MAISRC/ggplo... 0186
Jesse Onland @jdonland.bsky.social · 11/08/2026One day I'll remember that I want `fct_relevel()` and not `fct_reorder()`, but today is not that day. #tidyverse 000
Jesse Onland @jdonland.bsky.social · 04/08/2026Herbert Robbins (1915-2001) on the start of his career as a statistician: observing a physical Monte Carlo estimation of the number of bombs required to disable an airstrip. 010
Jesse Onland @jdonland.bsky.social · 28/07/2026I wondered what infrastructure and guidelines exist for #dataviz 📊 on @wikipedia.org, took a quick look, and now I regret it. A big jumble of half-baked, semi-official tools missing basic functionality, endless debate about whether pie charts are ever okay, no unified style guide. 000
Jesse Onland @jdonland.bsky.social · 24/07/2026Does anyone else's copy of @statmodeling.bsky.social, @avehtari.bsky.social and @rmcelreath.bsky.social's Bayesian Workflows have terrible colour registration? CRC is sending me a replacement copy, apparently. 110
Jesse Onland @jdonland.bsky.social · 16/07/2026The @ropensci.org website appears to be down. Alarming! 000
Reposted by Jesse Onland Xan Gregg @xangregg.bsky.social · 05/07/2026This fit didn't look like p=0.020 to me, so I extracted the data and checked. It looks like the Line+CI is for all the data, but the stats exclude the low outlier points. #dataviz jov.arvojournals.org/article.aspx... 182
Jesse Onland @jdonland.bsky.social · 06/07/2026This bicycle gear ratio visualizer reminds me of nomograms, and of the train timetable visualizations attributed to E. J. Marey. 📊 sheldonbrown.com/gear-graph.h... 020
Jesse Onland @jdonland.bsky.social · 02/07/2026What a bizarre choice of visualization for a sequence of six values. 020
Jesse Onland @jdonland.bsky.social · 24/06/2026Can Posit please hand over the tidyverse to some other organization that doesn't put 95% of its effort into LLM stuff? 030
Jesse Onland @jdonland.bsky.social · 17/06/2026I never realized how full of heresy Casella & Berger is. They think non-differentiable cumulative distribution functions represent pathological random variables not worthy of consideration! 000
Jesse Onland @jdonland.bsky.social · 08/06/2026Is looping LLM 📊 output through a prompt asking it to do a better job really better (cheaper? faster?) than just doing a good job oneself? www.goodeyelabs.com/insights/the...goodeyelabs.comThe Tufte Test: Teaching an AI Agent to Make Better Data VisualizationsI encoded Tufte's data visualization principles as a quality standard in Truesight, deployed it as an API, and pointed an AI agent at a real dataset. One instruction: keep improving until you pass. 141
Jesse Onland @jdonland.bsky.social · 07/06/2026Say what you will about Stephen Wolfram and his research programme, but you have to admit that the visualizations are cool. writings.stephenwolfram.com/2026/06/game...writings.stephenwolfram.comGames between Programs: The Ruliology of CompetitionStephen Wolfram applies ruliological methods to competition, considering all possibilities in looking for a winning strategy. Does competition lead to complexity or simplicity? 000
Jesse Onland @jdonland.bsky.social · 16/05/2026@flowingdata.com ought not to characterize keeping one's money under a mattress as having "favourable odds [of a positive return]". On the contrary, one is virtually certain to lose money, in real terms, by doing this. flowingdata.com/2026/05/14/m...flowingdata.comMore people losing money in prediction marketsFor the Washington Post, Jeremy B. Merrill and Leslie Shapiro visualized users who won and lost money on Polymarket. The odds aren’t great. A lot of users aren’t that good at predicting… 100
Reposted by Jesse Onland Voilà: Francis Gagnon @chezvoila.com · 21/04/2026Nice reminder and visual representation of the limitations of radar charts, by Flourish 📊 Source: flourish.studio/blog/create-... 0538
Reposted by Jesse Onland Michael Friendly @datavisfriendly.bsky.social · 28/03/2026📊 #OTD 🎂🎂🎂 Happy Minard Day! Charles Joseph Minard's, b. Mar 27, 1781, his big 245th. #OTD #dataviz One way to celebrate is to visit @infowetrust.com wonderful Visual Catalog of the Work of Charles Joseph Minard, bit.ly/3lOXsbR Another is my celebration of Minard Day, 2021 ed, bit.ly/49f7k1tbit.lyMinard Day 2021: Resources, Research and InspirationsMichael Friendly 12510
Reposted by Jesse Onland Voilà: Francis Gagnon @chezvoila.com · 28/03/2026A dozen year ago, I was alone at home and decided to treat myself to a beer and a detailed exploration of the famous Minard map. I wrote this blog post, which is still one of the most popular on our website all these years later. 📊 chezvoila.com/blog/minard-...chezvoila.com13 facts you didn't know about the Minard map - Voilà:Source: Wikipedia. The map representing the Russian campaign of the French army in 1812 is a true celebrity of the data visualization world, mostly known for its spectacular features. Lines show the n... 0142
Reposted by Jesse Onland Per Engzell @pengzell.bsky.social · 11/03/2026How far can you get in 60 minutes? European cities offer vastly larger areas reachable by public transit than US cities of comparable population size. Source: lconwell.github.io/lucasconwell... 1429299
Jesse Onland @jdonland.bsky.social · 10/03/2026See also: Blank Space by David W. Marx, which argues that aesthetic fragmentation and other forces have resulted in 21st century cultural stagnation. 010
Jesse Onland @jdonland.bsky.social · 08/03/2026Why do people mention which slop bot made something for them? Brand loyalty? Why not say nothing and let people think you used your own knowledge and abilities? 000
Jesse Onland @jdonland.bsky.social · 06/03/2026Posit is so embarrassing.posit.coIntroducing AI in RStudioToday we’re introducing AI in RStudio. We’ve embedded a specialized agent directly into RStudio so it can read your live session context and provide more accurate assistance for data science and analy... 000
Jesse Onland @jdonland.bsky.social · 05/03/2026What is with all the "📊 for kids" books lately? Is it just slop bots driving the cost of illustration to zero? Do parents really buy these to read to their kids? Is it a résumé padding exercise for the authors? 000
Jesse Onland @jdonland.bsky.social · 24/02/2026"Nothing is lost by adding the second graph." Sure, except for a consistent scale. 📊 040
Jesse Onland @jdonland.bsky.social · 23/02/2026The StatsCan website is baffling. Every dataviz product is meticulously documented with authorship, update cadence, underlying datasets, keywords, related outputs... everything but a link to the actual viz! 📊 030
Jesse Onland @jdonland.bsky.social · 14/02/2026I wonder whether the categorization of farmers into "large" and "small" in the data used for this visualization 📊 of income inequality in 19th c. France amounts to conditioning on the outcome. Or maybe it's by acreage? freerangestats.info/blog/2026/02... 120
Jesse Onland @jdonland.bsky.social · 13/02/2026From the first and second editions of @rmcelreath.bsky.social's Statistical Rethinking. 📊 000
Jesse Onland @jdonland.bsky.social · 07/02/2026Am I wrong to think that overlapping bars is just straightforwardly an error? Now area (and thus visual impact) is no longer proportional to the data. Maybe I'm too VDQI-pilled? #dataviz 📊 (Chart from SWD: Before & After) 110
Jesse Onland @jdonland.bsky.social · 07/02/2026Well, @newyorker.com... is this "re-signed" or "resigned"? Why leave this at a line break? You'll use the dieresis but not the double hyphen? 000
Jesse Onland @jdonland.bsky.social · 21/01/2026Chapter 6 of Casella & Berger is a real page-turner! It's a bit funny to read them introduce the likelihood principle and credible intervals while carefully avoiding the term "Bayesian". 010
Jesse Onland @jdonland.bsky.social · 02/01/2026"There is a strong relationship, but it isn't statistically significant." This frequentism stuff has absolutely cooked people's brains. 010
Jesse Onland @jdonland.bsky.social · 30/12/2025At first I thought I'd like this better with filled, triangular arrowheads, but upon further reflection I think this style makes it more obvious where the data points are. Is there an unconscious tendency to imagine the data point in the centre of a filled arrowhead instead of at the tip? 000
Jesse Onland @jdonland.bsky.social · 29/12/2025@allendowney.bsky.social on Hempel's raven paradox. I like the heatmaps visualizing the joint posterior distributions in each scenario. www.allendowney.com/blog/2025/12...allendowney.comThe Raven Paradox - Probably Overthinking ItSuppose you are not sure whether all ravens are black. If you see a white raven, that clearly refutes the hypothesis. And if you see a black raven, that supports the hypothesis in the sense that it in... 000
Jesse Onland @jdonland.bsky.social · 20/12/2025The archives of the journal Visible Language, which has published interesting articles on #dataviz 📊 in addition to typography, calligraphy, spelling reform, and many other interesting things, are available for free online: journals.uc.edu/index.php/vl...journals.uc.edu Archives | Visible Language 1157
Jesse Onland @jdonland.bsky.social · 03/12/2025Can you guess which basic #dataviz errors this graphic features? Why in the world wouldn't the colour mapping be the same across the four donuts? And why not a 100% stacked bar chart instead of donuts? Just like movies about making movies, data graphics about making data graphics are never good. 120
Reposted by Jesse Onland Evan Peck @peck.phd · 11/11/2025I'm not proud to tell you that I clicked this Wirecutter article fully believing it was about the 📊 Best Bar Charts. 1513
Reposted by Jesse Onland Vinni Ott @vlott.bsky.social · 29/08/2025New paper for anyone working with data: Better data viz - for free, in few clicks. Below, all N = 111, M = 0.04, SD = 0.27. One-sided t-tests vs. 0 yield: t(110) = 1.67, p = .049. Use raincloud plots. Or risk wrong conclusions! Plot w/ @jaspstats.bsky.social today! 🧪 📊 #PsychSciSky #StatsSky 🧵👇 77320
Jesse Onland @jdonland.bsky.social · 29/08/2025Will Posit's recent transition to hyping slop generation endanger its B Corporation status? Surely you can't be serious about climate targets while shilling this stuff, right? 000
Reposted by Jesse Onland Cédric Scherer @cedricscherer.com · 25/07/2025Find the data 🧐🤓 #dataviz #datatoinkratio 3162
Jesse Onland @jdonland.bsky.social · 17/07/2025Embarrassing. Why not just train a slop generator on all the conference submissions and then skip actually running it? 020
Jesse Onland @jdonland.bsky.social · 17/07/2025My struggles with Tableau 📊 seem to boil down to two issues: 1. Too little control over the aesthetic mapping. (E.g. cannot map to position.) 2. Dimensions and measures are treated radically differently (e.g by filtering) in ways that are unintuitive and/or just never what one would want. 220
Reposted by Jesse Onland EarthScope Consortium @earthscope.org · 17/07/2025Watch the seismic waves from today's magnitude 7.3 Alaska earthquake ripple across seismic stations in North America. More ➡️ loom.ly/kaJp5I0 1223211897
