Stephen Wild
@stephenjwild.bsky.social
I try to put straight lines through things but usually fail. Try to be Bayesian when I can. Views my own. RT/like != endorsement.
Reposted by Stephen Wild
Or, as written up in SIGBOIVK last year:
February 15, 2026 at 3:42 PM
Or, as written up in SIGBOIVK last year:
Reposted by Stephen Wild
A new blog post motivated from this amazing discussion with @akhilrao.bsky.social and @donskerclass.bsky.social
#EconSky #RStats #Stan
jamesblandecon.github.io/posts/2026-0...
#EconSky #RStats #Stan
jamesblandecon.github.io/posts/2026-0...
February 15, 2026 at 3:44 PM
A new blog post motivated from this amazing discussion with @akhilrao.bsky.social and @donskerclass.bsky.social
#EconSky #RStats #Stan
jamesblandecon.github.io/posts/2026-0...
#EconSky #RStats #Stan
jamesblandecon.github.io/posts/2026-0...
YouTube bad
like im getting euro nazi stuff now, dont like
February 15, 2026 at 12:36 PM
YouTube bad
Reposted by Stephen Wild
Another cool one is the reflection problem academic.oup.com/restud/artic...
Identification of Endogenous Social Effects: The Reflection Problem
Abstract. This paper examines the reflection problem that arises when a researcher observing the distribution of behaviour in a population tries to infer w
academic.oup.com
February 15, 2026 at 12:23 PM
Another cool one is the reflection problem academic.oup.com/restud/artic...
These posts are great because they suggest who to mute (everyone who gets mad about putting your cast iron in the dishwasher or who tries to tell how to care for it)
All my cast iron, fresh out of the dishwasher and ready to cook
February 15, 2026 at 1:54 AM
These posts are great because they suggest who to mute (everyone who gets mad about putting your cast iron in the dishwasher or who tries to tell how to care for it)
*chef's kiss*
Famous starry-eyed idealists like Stalin and Churchill.
February 15, 2026 at 12:36 AM
*chef's kiss*
Scream it from the rooftops
True causal inference has not been tried :)
More seriously: causal inference is not about prioritizing certain methods, it’s about being very clear about effect you are actually targeting (if any) and what assumptions justify your inferences.
More seriously: causal inference is not about prioritizing certain methods, it’s about being very clear about effect you are actually targeting (if any) and what assumptions justify your inferences.
February 14, 2026 at 6:58 PM
Scream it from the rooftops
10/10 response
What do you think Claude Code is?
February 13, 2026 at 11:34 PM
10/10 response
Reposted by Stephen Wild
Social media bad
A good friend had a baby a couple of years ago so I briefly signed up for fb with a burner email, told it I was a middle aged dude and got served a torrent of utterly hateful content, much of it targeting Trans people.
the minute the fb algorithm clocks you as a straight man it immediately sets about trying to destroy your life & endanger those around you
February 13, 2026 at 11:08 PM
Social media bad
Always retaliate first
The only thing necessary for the triumph of evil is for good players to not play tit-for-tat
February 13, 2026 at 10:48 PM
Always retaliate first
Reposted by Stephen Wild
Fair. I'm never quite sure how to take these conversations as I'm genuinely not sure (and not everyone is on the same page about) what journal articles are for. Nail that down and a Kasy-style decision theory exercise will sort out the rest, fine, but until then...
February 13, 2026 at 4:40 PM
Fair. I'm never quite sure how to take these conversations as I'm genuinely not sure (and not everyone is on the same page about) what journal articles are for. Nail that down and a Kasy-style decision theory exercise will sort out the rest, fine, but until then...
This a great case study in statistics, economics, and business. Why is their match rate is so high now, and can they maintain it as they expand?
"Our matches convert to actual dates at about 10x the rate of Tinder," Weng told TechCrunch.
A Stanford grad student created an algorithm to help his classmates find love; now, Date Drop is the basis of his new startup | TechCrunch
"Our matches convert to actual dates at about 10x the rate of Tinder," Weng told TechCrunch.
techcrunch.com
February 13, 2026 at 4:40 PM
This a great case study in statistics, economics, and business. Why is their match rate is so high now, and can they maintain it as they expand?
Hehehe
"Proper understanding of the answers of the above questions should in most cases make you at best ambivalent about DiD. If you still think you have a DiD problem, expect me to try to help you figure out what else you should do"
"Proper understanding of the answers of the above questions should in most cases make you at best ambivalent about DiD. If you still think you have a DiD problem, expect me to try to help you figure out what else you should do"
For Spring semester, I'm bringing back free weekly open office hours for anyone in the world with Econometrics questions.
Tuesdays 4-6 PM Central European Time (US EST 10AM-12PM) or by appointment; sign up and drop by!
Details and signup at: donskerclass.github.io/OfficeHours....
Tuesdays 4-6 PM Central European Time (US EST 10AM-12PM) or by appointment; sign up and drop by!
Details and signup at: donskerclass.github.io/OfficeHours....
February 13, 2026 at 1:10 PM
Hehehe
"Proper understanding of the answers of the above questions should in most cases make you at best ambivalent about DiD. If you still think you have a DiD problem, expect me to try to help you figure out what else you should do"
"Proper understanding of the answers of the above questions should in most cases make you at best ambivalent about DiD. If you still think you have a DiD problem, expect me to try to help you figure out what else you should do"
Reposted by Stephen Wild
Stats enthusiasts: I like to weave narratives using insights cross-tabbed from the latest poll
Stats experts: I only estimate conditional expectations and I keep a gun nearby so I can shoot them if they're from a distribution I don't recognize
Stats experts: I only estimate conditional expectations and I keep a gun nearby so I can shoot them if they're from a distribution I don't recognize
February 12, 2026 at 10:20 PM
Stats enthusiasts: I like to weave narratives using insights cross-tabbed from the latest poll
Stats experts: I only estimate conditional expectations and I keep a gun nearby so I can shoot them if they're from a distribution I don't recognize
Stats experts: I only estimate conditional expectations and I keep a gun nearby so I can shoot them if they're from a distribution I don't recognize
Stan bat signal
February 12, 2026 at 9:55 PM
Stan bat signal
Me, a genius: Q is at its profit-maximizing level when marginal revenue equals marginal cost
nothinghuman.substack.com/p/the-tyrann...
Being popular causes all kinds of bad context collapse phenomena
Being popular causes all kinds of bad context collapse phenomena
The Tyranny of the Marginal User
why consumer software gets worse, not better, over time
nothinghuman.substack.com
February 12, 2026 at 8:56 PM
Me, a genius: Q is at its profit-maximizing level when marginal revenue equals marginal cost
Having thought carefully* about this for 24 hours, my 2 cents as a non-academic about the discussion around this point.
1) there is a huge blurring of the is-ought distinction
2) the system is what the system does
*not really. Also I am thinking out loud right now
1/N
1) there is a huge blurring of the is-ought distinction
2) the system is what the system does
*not really. Also I am thinking out loud right now
1/N
Overall, I think our results are:
1. Believable. I think deep down we all know we publish "too many" significant results.
2. Disastrous. Selecting on significance in this way biases results across our whole literature away from zero & it stops us from learning what doesn't work.
1. Believable. I think deep down we all know we publish "too many" significant results.
2. Disastrous. Selecting on significance in this way biases results across our whole literature away from zero & it stops us from learning what doesn't work.
February 12, 2026 at 2:45 PM
Having thought carefully* about this for 24 hours, my 2 cents as a non-academic about the discussion around this point.
1) there is a huge blurring of the is-ought distinction
2) the system is what the system does
*not really. Also I am thinking out loud right now
1/N
1) there is a huge blurring of the is-ought distinction
2) the system is what the system does
*not really. Also I am thinking out loud right now
1/N
The Schitt's Creek gifs will continue until morale improves
February 12, 2026 at 11:42 AM
The Schitt's Creek gifs will continue until morale improves
*Wearing my Übergangsjacke*
9°C, misery. 10.5°C, bliss.
9°C, misery. 10.5°C, bliss.
look I don’t make the rules but Übergangsjacke has a clearly defined narrow temperature range.
February 11, 2026 at 3:29 PM
*Wearing my Übergangsjacke*
9°C, misery. 10.5°C, bliss.
9°C, misery. 10.5°C, bliss.
Reposted by Stephen Wild
That seems fine, but the Cox PH model can also be written instead in terms of the cumulative hazard, H(t), which doesn't condition on survival till time t anymore, so (1) doesn't hold and the rest of the argument falls apart
February 11, 2026 at 2:39 PM
That seems fine, but the Cox PH model can also be written instead in terms of the cumulative hazard, H(t), which doesn't condition on survival till time t anymore, so (1) doesn't hold and the rest of the argument falls apart
Two things (among many) that seem to pop out from this thread, the replies, and the QTs:
1) people do a lot out of spite
2) people who "aren't good at math" can learn math when either math becomes interesting to them or math is grounded in something that interests them.
No lessons here, I'm sure.
1) people do a lot out of spite
2) people who "aren't good at math" can learn math when either math becomes interesting to them or math is grounded in something that interests them.
No lessons here, I'm sure.
Funny story: my career in drones exists because I have a arithmetic learning disability, tested awfully in math and couldn’t study STEM in college, and became so angered by how normal it was to look down upon non-tech people in the 2010s that I decided to master a hard tech field out of pure spite.
February 11, 2026 at 2:39 PM
Two things (among many) that seem to pop out from this thread, the replies, and the QTs:
1) people do a lot out of spite
2) people who "aren't good at math" can learn math when either math becomes interesting to them or math is grounded in something that interests them.
No lessons here, I'm sure.
1) people do a lot out of spite
2) people who "aren't good at math" can learn math when either math becomes interesting to them or math is grounded in something that interests them.
No lessons here, I'm sure.
Always the Nurses' Health Study
February 11, 2026 at 11:42 AM
Always the Nurses' Health Study
THANK YOU FOR YOUR ATTENTION TO THIS MATTER
This means smartphones have probably expanded the sample of people who respond to surveys, even if they harm knowledge-based measures.
February 10, 2026 at 9:56 PM
THANK YOU FOR YOUR ATTENTION TO THIS MATTER