Sign in

Peter Ellis

@freerangestats.info
3.4K followers 1.9K following 3.2K posts

Director, Statistics for Development Division, at the Pacific Community. Posts are personal views, and most likely to be about data and #rstats, maybe with bits of history, social science and philosophy thrown in. Blog is at freerangestats.info.

PostsRepliesMedia
Peter Ellis @freerangestats.info · 12h
The world transition to renewable power seems to be going very well. Basically once the tech became cost-effective, a whole lot of old debates became irrelevant.
1110
Reposted by Peter Ellis
Brady West @bradytwest.bsky.social · 28/09/2026
A new version of the nonprobsvy package in R, and an article in JSS to boot! There is no better tool for the analysis of data from non-probability surveys, implementing all of the latest advances in this literature. If you analyze data from NP surveys, please read: www.jstatsoft.org/article/view...
jstatsoft.org
1147
Peter Ellis @freerangestats.info · 28/09/2026
Is there a term for effective altruism that is still interested in eg evidence for different development interventions and maximising ethical outcomes Peter Singer style, and hasn't gone insane through longtermism and AI obsession?
250
Reposted by Peter Ellis
Bart⚓️ @bartgonnissen.bsky.social · 23/09/2026
The Facial Expressions of Tethys by artist Julius von Bismarck. A suspended high-sea buoy that moves in real time. Sensors on a twin buoy out in the Atlantic Ocean send live satellite data to motors inside the museum. This makes the indoor buoy copy the exact, real-time movements of the ocean waves.
10381152812
Peter Ellis @freerangestats.info · 21/09/2026
The story in this thread is extraordinary and as far as I can tell, accurate.
010
Peter Ellis @freerangestats.info · 20/09/2026
A small #rstats blog post following up on last week's on sample size and the central limit theorem. How well does BCa bootstrap do in comparison to older methods for a confidence interval for the mean from a skewed population? Better, but not a magic fix. freerangestats.info/blog/2026/09...
Scatter plot comparing coverage of 95% confidence interval of BCa bootstrap with traditional CI calculated based on asymptotic normality. For various sample sizes and population distributions. BCa does better, but still less than the 95% one would hope.
081
Peter Ellis @freerangestats.info · 20/09/2026
It seems to me the AI companies could improve both their image and revenue if they poured billions of investment into working with experts on ethical, effective and people-friendly applications in a field like education, rather than solving maths problems and generating unneeded celebrities.
120
Peter Ellis @freerangestats.info · 17/09/2026
Wrote in a work email "we won't be sending anyone to the World Data Forum this year, partly because of budget, mostly because Riyadh is under a 'reconsider need to travel' advisory due to missile and drone attacks in the area", which seems kind of easy as management decisions go.
030
Reposted by Peter Ellis
Peter Nencka 📊 @peternka.bsky.social · 17/09/2026
🚨 Announcing OpenCensus, a new project with @ezrakarger.bsky.social : We are transcribing the historical US censuses and releasing them as open data 2.6 million people so far in 1940, browse here: opencensus.us
25926
Peter Ellis @freerangestats.info · 16/09/2026
Inspired by a @f2harrell.bsky.social comment, I did some #rstats simulations about how big a sample needs to be for the central limit theorem to kick in and the sample mean be normally distributed for inference purposes. Yes, with skewed data the answer is "lots". freerangestats.info/blog/2026/09...
Scatter plot with 8 facets, each showing a different distribution, and the actual coverage of a 95% confidence interval for the mean at different sample sizes. Most values are well below 95%.
33315
Peter Ellis @freerangestats.info · 16/09/2026
What do we call this phenomenon, where we are assailed with the near-identical one line summary of something multiple times. Not to pick on Reuters at all, this is a much bigger systemic thing. Sometimes we can go through 5 or 6 layers of Russian dolls of the same sentence over and over again.
060
Peter Ellis @freerangestats.info · 15/09/2026
Is there an interesting history about why the "responsible" in a RACI matrix (responsible, accountable, consulted, informed) as used by management consultants is so different from other traditions? In RACI, "responsible" means "does the work", rather than being responsible for decision or outcomes.
010
Reposted by Peter Ellis
Michael Friendly @datavisfriendly.bsky.social · 15/09/2026
📊 #rstats #dataviz My ggCheysson package was just re-submitted to CRAN 🤞 @infowetrust.com Brings the graphic style of Émile Cheysson's Albums de Statistique Graphique (1880s) to ggplot2: authentic color palettes, hatching patterns, and hand-drawn fonts. 🔗https://friendly.github.io/ggCheysson/
A 5x5 grid of thumbnail crops from Émile Cheysson's original 1880s-1900s statistical maps and diagrams, each labeled with its album year and plate number (e.g. "1880 MAP 7", "1906 MAP 50"), showing pie charts, bar charts, flow maps, and choropleth maps overlaid on maps of France and its regions in muted historical colors. Image from: @infowetrust
2255
Reposted by Peter Ellis
Elise Thomas @elisethomas.bsky.social · 12/09/2026
I think there's actually quite an easy and obvious way to solve the collective action problem of how to make the AI companies stop conducting risky research, and it's to make it very clear that they're legally liable for anything their models do. www.politico.com/news/2026/09...
politico.com
Anthropic CEO seeks immediate slowdown on AI
Dario Amodei warned that recent advances have begun to outpace the industry’s ability to fully understand and control the technology.
1286
Reposted by Peter Ellis
Giles Wilkes @gilesyb.bsky.social · 12/09/2026
aleximas.substack.com/p/will-ai-so... The best blog ever written on AI and growth, by a clear margin. By @aleximas.bsky.social
aleximas.substack.com
Will AI soon lead to double-digit growth?
Probably not. Here is why.
810334
Reposted by Peter Ellis
Robert (Bob) Kubinec @rmkubinec.bsky.social · 12/09/2026
This "going rogue" framing is nonsense. These are still just text analysis models. It's openAI that is "going rogue" by giving a computer program complete autonomy to make decisions without human oversight. That's a danger whether it's a fancy new LLM or an old-fashioned SQL database.
58617
Reposted by Peter Ellis
Peter Ellis @freerangestats.info · 11/09/2026
I'm in a technical field that's not software engineering, so I don't know how far this transfers. My general experience of more senior tech roles is not that they have better technical skills but have accumulated judgement, wider view, understanding of process and context compared to the juniors.
082
Reposted by Peter Ellis
Terence Tao @teorth.bsky.social · 11/09/2026
A group of 25 Fields Medalists, including myself, have made a joint declaration on Math and AI: mathandai.org . We welcome additional signatories. See also this article in the Economist announcing the declaration: www.economist.com/science-and-...
mathandai.org
Declaration — Math and AI
Read the declaration and add your name.
422052927
Reposted by Peter Ellis
Saloni @scientificdiscovery.dev · 05/09/2026
This is interesting. You get assigned to being born at a random place and time in history, to see what a typical person's life might have been like then. Unfortunately I was born in 1403 in the valley of Mexico and died at age 4 from dysentery.
anyhumanever.com
Any Human Ever
One life, drawn at random from all who have ever lived.
54547189
Peter Ellis @freerangestats.info · 05/09/2026
The games industry business model obviously doesn't incentivize this, but... are there computer games that, like chess, backgammon, poker or bridge, people are satisfied to just play this one game every week or day forever, gradually master, and never complain about needing new content?
430
Reposted by Peter Ellis
Emily Riederer @emilyriederer.bsky.social · 04/09/2026
Sidenote: this all illustrates an recurrent fascination of mine -- how often the blocked to good work is never having gotten to see "what good looks like" like if you've never seen a of datamart or an orchestrator, this feels reasonable. And DE has far fewer public examples than DS 12/
2132
Peter Ellis @freerangestats.info · 04/09/2026
Am half way through Henry James' The Wings of the Dove and really it is very tedious. Self absorbed characters with no interest in the world other than who has a crush on whom and playing games hiding stuff. Pages of repetitive introspection. Sentences and paragraphs way too long. What am I missing?
020
Reposted by Peter Ellis
Our World in Data @ourworldindata.org · 31/08/2026
📊 New data: World Development Indicators, July 2026 release The World Development Indicators (WDI) is the World Bank’s compilation of statistics on global development.
A thumbnail image showing the landing page for the World Bank's World Development Indicators dataset
1187
Reposted by Peter Ellis
Ben Recht @beenwrekt.bsky.social · 30/08/2026
The overreaction to this Hugging Face thing is driving me nuts. Come flay me for being wrong but... 1/x
14436126
Peter Ellis @freerangestats.info · 29/08/2026
At a function last night someone asked how old I was and said 'you look pretty well for someone your age'. This clashes with my self image as a young man starting out in life.
060
Peter Ellis @freerangestats.info · 28/08/2026
I see Samoa's vaccination and measles record are in the news. Coincidentally yesterday I gave a talk with these relevant charts. Nasty spike in DALYs lost from measles along with the outlier low point vaccinations.
000
Reposted by Peter Ellis
Marc Kissel @marckissel.bsky.social · 25/08/2026
Im Teaching a data science for anthropology class using #rstats. Most never coded before/worked w/ command line interface so I live demoed using one via playing Zork, the text adventure game. They were amused how excited I got when I found the sword :). Plus fun way to intro a CLI environment.
3254
Peter Ellis @freerangestats.info · 19/08/2026
There is sort of a law with this kind of technology that the writers are relying on, you can't know in advance how it will make something taste worse than fresh products, but you can be confident it will somehow. See also the Sirius Cybernetics Nutrimatic Drinks Dispenser.
100
Peter Ellis @freerangestats.info · 18/08/2026
"SLR" is an acronym I get regularly confused by. In my work (but not my day to day work) it often means "sea level rise" but I can't help thinking either self-loading rifle or single-lens reflex, and having to look up "what do they mean by *that* here?".
120
Reposted by Peter Ellis
Richard D. Morey @richarddmorey.bsky.social · 18/08/2026
Nothing in my experimental-cognitive/math-psych background could have prepared me for the unique horror of large-scale routinely-collected medical and educational data
810313
Peter Ellis @freerangestats.info · 13/08/2026
Thinking more about this. One thing I'd pay for is a subscription that gives me access to paywalled articles linked here, from dozens of publications I'd never otherwise subscribe to, with bluesky clipping the ticket on the way through. But I dont think this model works for the end publications.
150
Peter Ellis @freerangestats.info · 13/08/2026
I am interested in folks' take on the statement "the global pandemic outlook is worsening", both in terms of more frequent and damaging infectious disease outbreaks and world preparedness for the next big one. Is this true? Or is it More Complicated Than that?
000
Peter Ellis @freerangestats.info · 12/08/2026
US crude oil stocks recovered slightly in the latest weekly EIA data - little fishhook in the blue line in this chart. freerangestats.info/fuel-crisis/...
Line chart of US total crude oil stocks 2000 to present
010
Reposted by Peter Ellis
Saloni @scientificdiscovery.dev · 11/08/2026
BIG NEW piece by me. A few years ago, if you asked me to summarize my entire worldview in one article, I would’ve said it was too broad and too difficult. But this year, I decided to do it.
worksinprogress.co
Every disease is a policy failure
Few people know how much medicine has progressed in their lifetimes. Fewer know how much faster it could be progressing.
1327189
Reposted by Peter Ellis
Robert Komaniecki @komaniecki.bsky.social · 12/08/2026
Priest: And make sure to put the letter "M" at the beginning of the sheet music. Scribe: No problem boss. Priest: But just a normal "M." Nothing crazy. Scribe: Why did you say it like that
08614
Peter Ellis @freerangestats.info · 11/08/2026
A common experience for me is hybrid Teams meetings with a large group in one room and others at their work stations. When the room's sound is substandard it seems to be literally impossible to train people to only speak close to a microphone. Is there any trick to making this a social necessity?
121
Reposted by Peter Ellis
Eva Vivalt @evavivalt.bsky.social · 10/08/2026
What happens when someone receives $1,000/month for 3 years? The effects don't stop with the recipient. In this new NBER working paper, we examine what changed for partners, households, friends & family after 1,000 people received $1,000/month with 2,000 in a control group. 🧵1/
27627
Reposted by Peter Ellis
Ben Hanowell @hanowell.me · 10/08/2026
I think Bick's got it right. www.stlouisfed.org/on-the-econo...
stlouisfed.org
What’s Behind the Sharp Drop in Labor Force Participation?
In the first half of 2026, the falling labor force participation rate was mostly due to a statistical correction and an aging population. But a sharp drop in prime-age workers also occurred.
183
Peter Ellis @freerangestats.info · 10/08/2026
I discovered today that sunscreen trutherism is a thing, and seems to come from a very basic causal/DAG/statistical misunderstanding. Some observational research shows people who put on more sunscreen get more skin cancer (obviously because 'going out in the sun' leads to both).
5222
Reposted by Peter Ellis
Branko Milanovic @brankomilan.bsky.social · 09/08/2026
The 2026 version of All the Ginis is out: stonecenter.gc.cuny.edu/publications...
stonecenter.gc.cuny.edu
All the Ginis (ALG) Dataset - Stone Center on Socio-Economic Inequality
This dataset, constructed by Stone Center Senior Scholar Branko Milanovic, represents a compilation and adaptation of income or consumption Gini coefficients (calculated across households or household...
1208
Peter Ellis @freerangestats.info · 09/08/2026
What's striking about this graphic is how unusual Clinton's popularity was; the only president to increase popularity broadly through his term it looks to me, and he did it even with the other party's supporters not just his own. Even more striking compared with his successors than his predecessors.
120
Peter Ellis @freerangestats.info · 08/08/2026
I have added to my little personal collection of fuel-crisis-monitoring charts a plot of the retail prices of petrol/gasoline and diesel, in USA and New Zealand (where filling your car, quite rightly, costs US$7 per gallon). Blog and #rstats code at freerangestats.info/blog/2026/08...
Time series chart of petrol and diesel prices in New Zealand and USA since 2004, with the GFC, '$100 crude plateau', shale oil hitting the market, Russian invasion of Ukraine, and Iran attack on Iraq all marked.
150
Reposted by Peter Ellis
Emi Tanaka @emitanaka.org · 06/08/2026
📢🇦🇺 Australian National University is recruiting a continuing Senior Data Scientist 👩‍💻🧑‍💻 Bring your statistical expertise and help turn data into meaningful university-wide insights 📊 📅 Apply by 23 Aug 2026 23:55 AEST #Statistics #StatsJobs jobs.anu.edu.au/jobs/senior-...
jobs.anu.edu.au
Senior Data Scientist - Canberra / ACT, ACT, Australia
Classification: ANU Senior Manager 1 (Administration)Salary package: $141,637 - $148,403 per annum plus 17% superannuationTerms: Full-time, Continuing The Position Operating under broad strategic guid...
0117
Peter Ellis @freerangestats.info · 05/08/2026
US crude oil stocks (including Strategic Petroleum Reserve) arrested their downwards slide in the latest data. They are now 20 weeks of linear decline from reaching a theoretical stress point of 30 days refinery cover; an improvement from 19 weeks a week ago. freerangestats.info/fuel-crisis/...
time series plot of US total crude oil stocks 2000 to now.
121
Reposted by Peter Ellis
Rob Hyndman @robjhyndman.com · 03/08/2026
On Thursday, I'm giving the last of the 2026 Ihaka lectures on "Spotting the weird ones" (about anomaly detection using #rstats). It's an honour to speak at something named after Ross Ihaka. It will be live-streamed for those who can't be there. www.auckland.ac.nz/en/science/a...
auckland.ac.nz
Ihaka Lecture Series – University of Auckland
The Ihaka Lecture Series is an annual event hosted by the Department of Statistics which presents the latest research about statistics and computer science.
0336
Peter Ellis @freerangestats.info · 01/08/2026
I couldn't find the exact annotated plot of total US oil stocks I wanted, so I had to make my own. At the rate of decline since its recent peak, there are 19 weeks left to having 30 days cover of refinery needs. Blog with #rstats code at freerangestats.info/blog/2026/08...
time series chart of total US crude oil stocks, including SPR, since 2000. Shows sharp decline in last few months. Point is labelled 712 million barrels, 41 days of refinery cover. Subtitle says that at rate of net decline since 3 April (10.4 million barrels per week), there are 19 weeks to a point of having only 30 days of refinery cover.
0133
Peter Ellis @freerangestats.info · 01/08/2026
I guess the 'Infantino for UN Secretary-General' campaign has hit a snag.
020
Reposted by Peter Ellis
👻Really Spooky Smith👻 @reallyseansmith.bsky.social · 28/07/2026
"Guilty pleasure" presumes I feel any guilt about it.
Bell curve meme with "I like The Monkees" at the high and low ends and crying guy going THE MONKEES WERE A FAKE BAND COOKED UP BY TWO TV PRODUCERS FOR A SITCOM
2183
Reposted by Peter Ellis
Jonathan Brewer @kiwibrew.bsky.social · 28/07/2026
I've open-sourced a web service container that will give you a WorldPop population count anywhere on earth given a point (100x100m), a point + radius, or a geojson polygon. It's using R2025A at the moment, but can change as needed. github.com/InternetSoci...
github.com
GitHub - InternetSociety/wpopapi: API for accessing WorldPop data
API for accessing WorldPop data. Contribute to InternetSociety/wpopapi development by creating an account on GitHub.
163