BIG IF TRUE
Probably right, and interesting if so.
Data-science pieces that start from what I live, read, play and scroll through, built from open data by guiding an AI model. Every issue ends with its cards on the table: code, data and the errors we found.
Read and subscribeHow it worksEvery issue has three beats
BIG
The fact. One figure, one claim, stated as plainly as the data allows.
IF
A closer look at what the first figure measures, and what it misses. Sometimes it corrects it; sometimes it adds what the figure could not show.
TRUE
The extension: what IF leaves standing, taken beyond the case it started from.
Issues
Southern Europe has stopped cooling down at night
Tropical nights and hours of relief in ERA5-Land, 2020–25 against 1980–89, weighted by population.
Read the article Leggi in italiano Figures, data and code
T1: the Korean esports team that transforms in October
Elo ratings for every professional League of Legends game since 2011, and the one team they keep getting wrong at the World Championship.
Read the article Short version Leggi in italiano Figures, data and code On Substack
Who is winning F1, Kimi Antonelli or his Mercedes?
Elo ratings for every Formula 1 driver and car since 1950, and how much of a driver's edge is the car.
Read the article Leggi in italiano Dashboard Figures, data and code On Substack
Italy doesn't have a petrol price. It has several
What you pay at the pump depends on where you fill up, and only partly on oil.
coming soon
All issues and how each is archived →
Cards on the table
Which model did what. The real errors found and fixed. The peer-reviewed work on the same question, and whether it agrees. Code that collects the data, the data itself where the licence allows, and a DOI to cite.
Nothing here is peer-reviewed. That is why the checking is left to you: check it yourself.