@matterofstats on Twitter
"Your data is not required to follow a well-defined distribution"
- personas for how different people will use the tool,
- decisions that can be made with said tool, and
- actions made with it
- personas for how different people will use the tool,
- decisions that can be made with said tool, and
- actions made with it
Had an MAE in 2025 of under 4 rating points
Had an MAE in 2025 of under 4 rating points
#VeryFirstWorldProblems
#VeryFirstWorldProblems
www.matterofstats.com/general-probability-and-statis/2025/12/20/does-a-contestants-self-described-job-title-tell-us-anything-more
www.matterofstats.com/general-probability-and-statis/2025/12/20/does-a-contestants-self-described-job-title-tell-us-anything-more
www.matterofstats.com/general-probability-and-statis/2025/12/20/does-a-contestants-self-described-job-title-tell-us-anything-more
BIG NERD DESIGN ENERGY 🫦
BIG NERD DESIGN ENERGY 🫦
The results are quite sensitive in aggregate to needing the controls. Here's the replication of Figure 3, including the case w/o controls:
Jam made from a ram’s tail end? (9)
Spread from fruit, mostly orange, made at home (9)
Sweet preserve made when a dram’s ale is mixed (9)
We're still safe... for now
CC @dontattempt.bsky.social
Jam made from a ram’s tail end? (9)
Spread from fruit, mostly orange, made at home (9)
Sweet preserve made when a dram’s ale is mixed (9)
We're still safe... for now
CC @dontattempt.bsky.social