Andi Fugard
@andifugard.info
Social policy evaluator. London-based, Belfast-born. They/them. Personal account – views mine. Posts auto delete after a month.
Mastodon: https://sciences.social/@andi
Web: https://andifugard.info/
DM: https://andifugard.info/contact/
Mastodon: https://sciences.social/@andi
Web: https://andifugard.info/
DM: https://andifugard.info/contact/
Any Mersenne Twister experts out there? Based on some experiments, I suspect that the longest initial run of identical values, that is all 0s or all 1s, from rbinom in R is 32. Since that's a power of 2, wonder whether it's an artifact of the algorithm. #RStats
andifugard.info/a-mersenne-m...
andifugard.info/a-mersenne-m...
A Mersenne Mind-Twister – Andi Fugard (∧⇒)
andifugard.info
November 8, 2025 at 10:19 AM
Any Mersenne Twister experts out there? Based on some experiments, I suspect that the longest initial run of identical values, that is all 0s or all 1s, from rbinom in R is 32. Since that's a power of 2, wonder whether it's an artifact of the algorithm. #RStats
andifugard.info/a-mersenne-m...
andifugard.info/a-mersenne-m...
Reposted by Andi Fugard
All very nice but please consider how the message will be understood by those of us who weren’t born here. You risk replacing one exclusion with another.
November 6, 2025 at 3:39 PM
All very nice but please consider how the message will be understood by those of us who weren’t born here. You risk replacing one exclusion with another.
Reposted by Andi Fugard
Which one is more English?
November 6, 2025 at 11:58 AM
Which one is more English?
Reposted by Andi Fugard
"Isolation" at Gorse runs from 8.30am to 3.05pm and sees pupils having their lunch in the room and not being allowed to socialise with other students.
November 3, 2025 at 3:54 PM
"Isolation" at Gorse runs from 8.30am to 3.05pm and sees pupils having their lunch in the room and not being allowed to socialise with other students.
Reposted by Andi Fugard
The Gorse Academies Trust’s current behaviour policy also sees pupils facing what it itself calls “Isolation” for “lines in their eyebrows,” uniform violations or forgetting their student planner twice.
November 3, 2025 at 3:52 PM
The Gorse Academies Trust’s current behaviour policy also sees pupils facing what it itself calls “Isolation” for “lines in their eyebrows,” uniform violations or forgetting their student planner twice.
Reposted by Andi Fugard
New: Academy trust cuts sanction for children with “inappropriate hairstyles” from three days in isolation to two:
educationuncovered.co.uk/news/academy...
educationuncovered.co.uk/news/academy...
Education Uncovered | News| Academy trust cuts sanction for children with “inappropriate hairstyles” from three days in isolation to two
Pupils at the Gorse Academies Trust also face “isolation” for “lines in their eyebrows,” for uniform violations, or for forgetting their student planner twice, its behaviour policy states. However, th...
educationuncovered.co.uk
November 3, 2025 at 3:52 PM
New: Academy trust cuts sanction for children with “inappropriate hairstyles” from three days in isolation to two:
educationuncovered.co.uk/news/academy...
educationuncovered.co.uk/news/academy...
Reposted by Andi Fugard
found the random seeds used in the opening scene of Rosencrantz and Guildenstern Are Dead
November 3, 2025 at 12:54 AM
found the random seeds used in the opening scene of Rosencrantz and Guildenstern Are Dead
If you take 30 draws from a Bernoulli distribution, e.g., to randomise people to one of two conditions, there’s a 1/536,870,912 chance that all 30 will be assigned to the same condition. Try seeds 236903047 and 627034302 with rbinom(30, 1, .5) in #RStats
Read more: andifugard.info/totally-rand...
Read more: andifugard.info/totally-rand...
Totally random – Andi Fugard (∧⇒)
andifugard.info
November 3, 2025 at 12:12 AM
If you take 30 draws from a Bernoulli distribution, e.g., to randomise people to one of two conditions, there’s a 1/536,870,912 chance that all 30 will be assigned to the same condition. Try seeds 236903047 and 627034302 with rbinom(30, 1, .5) in #RStats
Read more: andifugard.info/totally-rand...
Read more: andifugard.info/totally-rand...
Reposted by Andi Fugard
Two suspects detained in connection with London-bound train stabbings
Two suspects detained in connection with London-bound train stabbings
Police have not yet disclosed a motive behind the stabbing attack at a train headed to the capital, London, which injured ten people, nine of them critically. Officials say investigations into the incident are still ongoing with the two detained suspects.
l.euronews.com
November 2, 2025 at 10:01 AM
Two suspects detained in connection with London-bound train stabbings
I'm out and about and the rain has just stopped. What I want to know is whether the clouds floated off or I walked away from the clouds.
November 1, 2025 at 4:41 PM
I'm out and about and the rain has just stopped. What I want to know is whether the clouds floated off or I walked away from the clouds.
Reposted by Andi Fugard
Wait until you learn about common ways of doing segmentation analysis in marketing.
"Yeah, we ran a K-means algorithm, gave each cluster a cute name and a persona, and now we're making every decision based on whether Pumpkin-Spice Peggy or Truck-Nut Terry will like it".
"Yeah, we ran a K-means algorithm, gave each cluster a cute name and a persona, and now we're making every decision based on whether Pumpkin-Spice Peggy or Truck-Nut Terry will like it".
It’s astonishing how many researchers seem to believe that a cluster analysis is such a sensible analysis that it needn’t even be justified through a coherent research question. Just cluster analysis go brrrrr
October 27, 2025 at 7:10 PM
Wait until you learn about common ways of doing segmentation analysis in marketing.
"Yeah, we ran a K-means algorithm, gave each cluster a cute name and a persona, and now we're making every decision based on whether Pumpkin-Spice Peggy or Truck-Nut Terry will like it".
"Yeah, we ran a K-means algorithm, gave each cluster a cute name and a persona, and now we're making every decision based on whether Pumpkin-Spice Peggy or Truck-Nut Terry will like it".
Reposted by Andi Fugard
Bonus points if you find clusters that you label as "low" "medium" "high" and "mixed"
It’s astonishing how many researchers seem to believe that a cluster analysis is such a sensible analysis that it needn’t even be justified through a coherent research question. Just cluster analysis go brrrrr
October 27, 2025 at 6:02 PM
Bonus points if you find clusters that you label as "low" "medium" "high" and "mixed"
Reposted by Andi Fugard
It’s astonishing how many researchers seem to believe that a cluster analysis is such a sensible analysis that it needn’t even be justified through a coherent research question. Just cluster analysis go brrrrr
October 27, 2025 at 3:42 PM
It’s astonishing how many researchers seem to believe that a cluster analysis is such a sensible analysis that it needn’t even be justified through a coherent research question. Just cluster analysis go brrrrr
Reposted by Andi Fugard
After following lots of economists on social media for the last 10+ years I think agricultural economists should rebrand as “less upity economists” or “economists without pretenses” or possibly “literally bean counters”
October 26, 2025 at 8:32 PM
After following lots of economists on social media for the last 10+ years I think agricultural economists should rebrand as “less upity economists” or “economists without pretenses” or possibly “literally bean counters”
Reposted by Andi Fugard
I debated 20 far-far-far-right conservatives (racists? fascists?) on Jubilee's 'Surrounded.'
Here are some of the highlights of them unable to answer my basic questions or rebut the simplest of points. Not sure whether to laugh or cry.
Here's the full 'debate': www.youtube.com/watch?v=2S-W...
Here are some of the highlights of them unable to answer my basic questions or rebut the simplest of points. Not sure whether to laugh or cry.
Here's the full 'debate': www.youtube.com/watch?v=2S-W...
July 20, 2025 at 3:01 PM
I debated 20 far-far-far-right conservatives (racists? fascists?) on Jubilee's 'Surrounded.'
Here are some of the highlights of them unable to answer my basic questions or rebut the simplest of points. Not sure whether to laugh or cry.
Here's the full 'debate': www.youtube.com/watch?v=2S-W...
Here are some of the highlights of them unable to answer my basic questions or rebut the simplest of points. Not sure whether to laugh or cry.
Here's the full 'debate': www.youtube.com/watch?v=2S-W...
Fine then, I'll use a different seed
> set.seed(1330296)
> rbinom(25, 1, .5)
[1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
> set.seed(1330296)
> rbinom(25, 1, .5)
[1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
We need to have a conversation about random seeds. Don't use 42.
blog.genesmindsmachines.com/p/if-your-ra...
blog.genesmindsmachines.com/p/if-your-ra...
If your random seed is 42 I will come to your office and set your computer on fire🔥
Figuratively. More likely you'll get a stern talking to.
blog.genesmindsmachines.com
October 23, 2025 at 8:48 PM
Fine then, I'll use a different seed
> set.seed(1330296)
> rbinom(25, 1, .5)
[1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
> set.seed(1330296)
> rbinom(25, 1, .5)
[1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
I've reached the deliberately leaving signs of AI in replies to emails that were obviously written using AI phase of late stage capitalism 🤖✉️ #AI #Emails #Capitalism #Signs
October 22, 2025 at 10:30 AM
I've reached the deliberately leaving signs of AI in replies to emails that were obviously written using AI phase of late stage capitalism 🤖✉️ #AI #Emails #Capitalism #Signs
Reposted by Andi Fugard
Hello, friends! After 10(!) years of #AdventOfCode, I've made some changes to preserve my sanity: there will be 12 days of puzzles each December (still starting Dec 1) and there is no longer a global leaderboard. Read more:
adventofcode.com/2025/about#f...
adventofcode.com/2025/about#f...
adventofcode.com/2025/about#f...
adventofcode.com/2025/about#f...
October 22, 2025 at 2:32 AM
Hello, friends! After 10(!) years of #AdventOfCode, I've made some changes to preserve my sanity: there will be 12 days of puzzles each December (still starting Dec 1) and there is no longer a global leaderboard. Read more:
adventofcode.com/2025/about#f...
adventofcode.com/2025/about#f...
adventofcode.com/2025/about#f...
adventofcode.com/2025/about#f...
Reposted by Andi Fugard
Today is the day 👀
Happy to announce that I'll give a talk on how we can make rigorous causal inference more mainstream 📈
You can sign up for the Zoom link here: tinyurl.com/CIIG-JuliaRo...
You can sign up for the Zoom link here: tinyurl.com/CIIG-JuliaRo...
October 20, 2025 at 5:47 AM
Today is the day 👀
Em-dashes, particularly used outside LaTeX, and "delve" are or were clues of LLM use. How about "that said"? I feel I've noticed that becoming more common.
October 19, 2025 at 4:25 PM
Em-dashes, particularly used outside LaTeX, and "delve" are or were clues of LLM use. How about "that said"? I feel I've noticed that becoming more common.
Reposted by Andi Fugard
October 18, 2025 at 6:48 PM
Something fun (Słoczyński et al., 2025):
“[Inverse probability tilting] coincides with Hainmueller’s (2012) entropy balancing estimator when the propensity score is estimated with the logit model”.
I had a quick look using @noahgreifer.bsky.social's WeightIt package andifugard.info/entropy-bala...
“[Inverse probability tilting] coincides with Hainmueller’s (2012) entropy balancing estimator when the propensity score is estimated with the logit model”.
I had a quick look using @noahgreifer.bsky.social's WeightIt package andifugard.info/entropy-bala...
Entropy balancing and inverse probability tilting – Andi Fugard (∧⇒)
andifugard.info
October 18, 2025 at 10:43 AM
Something fun (Słoczyński et al., 2025):
“[Inverse probability tilting] coincides with Hainmueller’s (2012) entropy balancing estimator when the propensity score is estimated with the logit model”.
I had a quick look using @noahgreifer.bsky.social's WeightIt package andifugard.info/entropy-bala...
“[Inverse probability tilting] coincides with Hainmueller’s (2012) entropy balancing estimator when the propensity score is estimated with the logit model”.
I had a quick look using @noahgreifer.bsky.social's WeightIt package andifugard.info/entropy-bala...
Reposted by Andi Fugard
Box breakers live outside the narrow demands of gender, sex and sexuality categories.
They are the residue of design practices – the people left behind after everyone else has been organised into neat, tidy boxes.
They are the residue of design practices – the people left behind after everyone else has been organised into neat, tidy boxes.
October 13, 2025 at 11:47 AM
Box breakers live outside the narrow demands of gender, sex and sexuality categories.
They are the residue of design practices – the people left behind after everyone else has been organised into neat, tidy boxes.
They are the residue of design practices – the people left behind after everyone else has been organised into neat, tidy boxes.
Reposted by Andi Fugard
What I'm listening to today: "Olson"
Boards of Canada arranged to play on a DEC PDP-1 from 1959. The PDP-1 doesn't have sound, but it does have front-panel light bulbs for debugging, so they rewired the light bulb lines into speakers to create 4 square wave channels
www.youtube.com/watch?v=wubk...
Boards of Canada arranged to play on a DEC PDP-1 from 1959. The PDP-1 doesn't have sound, but it does have front-panel light bulbs for debugging, so they rewired the light bulb lines into speakers to create 4 square wave channels
www.youtube.com/watch?v=wubk...
Boards of Canada "Olson" on a 1959 PDP-1 Computer
YouTube video by Joe Lynch
www.youtube.com
October 12, 2025 at 7:02 PM
What I'm listening to today: "Olson"
Boards of Canada arranged to play on a DEC PDP-1 from 1959. The PDP-1 doesn't have sound, but it does have front-panel light bulbs for debugging, so they rewired the light bulb lines into speakers to create 4 square wave channels
www.youtube.com/watch?v=wubk...
Boards of Canada arranged to play on a DEC PDP-1 from 1959. The PDP-1 doesn't have sound, but it does have front-panel light bulbs for debugging, so they rewired the light bulb lines into speakers to create 4 square wave channels
www.youtube.com/watch?v=wubk...