Thom Volker
@thomvolker.bsky.social
📤 330
📥 311
📝 691
PhD Candidate in Statistics, Utrecht University Creates fake data for a living. thomvolker.github.io
reposted by
Thom Volker
Andrea Pitzer
16 days ago
When there are no consequences for the last bad thing, you'll get a next worse thing.
26
3959
1150
I’m convinced some professors do get paid per article. Why on earth would you otherwise crank out 200 papers per year?
add a skeleton here at some point
1 day ago
1
2
0
reposted by
Thom Volker
Dmitry Grozoubinski
3 days ago
Inside the Department of War are two wolves: "We've shut down the Colleges of War because book learnings are woke, gay, and irrelevant to war fighting." "How come no one told us the Strait is important, there are different kinds of Kurds, Iran is big, and air power historically doesn't win wars?"
116
9117
2412
reposted by
Thom Volker
Ted McCormick
3 days ago
"I got my PhD by writing prompts instead of doing research, I'm winning" got some bad news, there still no jobs and now you also know nothing
81
6986
1235
reposted by
Thom Volker
Do you struggle with missing data in your statistical analyses? Come join our Summer School "Solving Missing Data Problems in R"! We will tell you when you can safely use complete case analysis, and when more dedicated strategies are required!
utrechtsummerschool.nl/courses/data...
3 days ago
0
29
17
Is ChatGPT trained on Hegseth, or is Hegseth trained on ChaptGPT?
add a skeleton here at some point
3 days ago
0
1
0
The people with the strapped cameras be like: (it's in Dutch, but I promise you don't need to understand the language)
add a skeleton here at some point
3 days ago
0
0
0
I went to LinkedIn to promote this, but holy moly, is there any human-written content there still? Literally every post is overloaded with unnecessary contrasts and an emoji before every paragraph
add a skeleton here at some point
3 days ago
1
10
1
The course is offered by the mice development team in Utrecht, The Netherlands, and will cover how to deal with imputation in classical inference settings as well as prediction modelling. Housing can be provided as well!
add a skeleton here at some point
3 days ago
0
7
1
Do you struggle with missing data in your statistical analyses? Come join our Summer School "Solving Missing Data Problems in R"! We will tell you when you can safely use complete case analysis, and when more dedicated strategies are required!
utrechtsummerschool.nl/courses/data...
3 days ago
0
29
17
reposted by
Thom Volker
Rafe Meager (they/them)
5 days ago
what function is the biggest jumpscare to you. i'll go first, clear choice for me at least it's obviously the gamma function.
34
107
27
reposted by
Thom Volker
Thomas Steinke
4 days ago
Some people are still debating whether or not LLMs are "useful," so let's stake out one clear use case: LLMs are useful for translating between languages. That includes translating between natural languages (e.g. Spanish to English) and, more recently, to formal languages (e.g. English to Python).
3
34
2
reposted by
Thom Volker
Julia M. Rohrer
5 days ago
phd students hungry for those rare candies to finally level up
1
6
1
Oh and reviewer 2 is the personification of Team Rocket
add a skeleton here at some point
5 days ago
0
0
0
Doing a PhD is like playing Pokémon: sure, you want to beat the final gym leader, but the sidequests are what make it fun.
5 days ago
2
22
6
I want an app that turns every instance of "utilize" into "use"
add a skeleton here at some point
5 days ago
2
4
1
reposted by
Thom Volker
Lotfi El Hamidi
7 days ago
1. Iran had en heeft geen kernwapens maar heeft nu duizend redenen om ze nu wel te hebben. 2. Spanje? Je bedoelt het land dat de genocide in Gaza wilde stoppen? The audacity.
add a skeleton here at some point
6
93
19
reposted by
Thom Volker
Vincent Arel-Bundock
7 days ago
In any case, all author proceeds go to the Native Women's Shelter of Montreal and Against Malaria Foundation. First two receipts below. If you use the website or software, please consider donating. And let me know if you do; it'll make my day. Links below. 🙏 7/9
1
46
5
reposted by
Thom Volker
Scott Shapiro
8 days ago
“KID, WE NEED YOUR GAS”
5
469
87
Suddenly the Bayesians don't like using prior information no more
add a skeleton here at some point
7 days ago
1
2
1
"We are going to get a gun. Not one of the woke guns but one of the VERY powerful guns. And we are going to shoot in our own foot very strongly. Frankly, we are going to shoot in our own foot stronger than ANY OTHER COUNTRY ever did before."
add a skeleton here at some point
7 days ago
0
2
0
Literally no one: Scientific reports: "... warm from move make more hot"
add a skeleton here at some point
7 days ago
0
4
0
If you refuse to share your code, I refuse to take your results seriously.
add a skeleton here at some point
8 days ago
2
24
2
reposted by
Thom Volker
David Ho
8 days ago
Most men who changed history also had women who enabled them.
loading . . .
100 Years of Women Who Changed History (Gift Article)
Revisiting the obituaries of a century of notable women to show how they were remembered — and what history may have left unsaid.
https://www.nytimes.com/interactive/2026/03/06/obituaries/archives/notable-women-deaths-obituaries.html?unlocked_article_code=1.RlA.WLlb.Tj0JzNAuYzIt&smid=url-share
2
81
27
reposted by
Thom Volker
Dan Quintana
9 days ago
I’m reminded of this comic almost every time I check LinkedIn
8
1339
269
reposted by
Thom Volker
Darth Putin
11 days ago
Should I offer Kristi Noem asylum?
68
641
83
reposted by
Thom Volker
econmaett
12 days ago
Do you know any other cool interactive applications that illustrate some statistical concept?
#rstats
#stats
@rpsychologist.com
rpsychologist.com/likelihood/
loading . . .
Understanding Maximum Likelihood Estimation
A tool to understand maximum likelihood estimation
https://rpsychologist.com/likelihood/
12
47
19
Which, I think, is a very fair point of view, given that anyone can make their package available via GitHub. So, if you want to enjoy the benefits CRAN offers, you must put in some work to accommodate the end-user.
add a skeleton here at some point
12 days ago
0
6
1
DDoSing openai but then with queries it is, people
add a skeleton here at some point
12 days ago
0
2
0
reposted by
Thom Volker
Michael Hobbes
13 days ago
Straightforward right-wing agitprop. The idea that thousands of kids were pushed into gender-affirming surgeries because the left shuts down debate is a laughable conspiracy theory. The overwhelming social pressure is to be cis, not trans!
26
2160
273
reposted by
Thom Volker
Darren Dahly
13 days ago
"GDPR is ruining everything"
add a skeleton here at some point
1
28
14
reposted by
Thom Volker
Matthew Kay
13 days ago
shocking you'd rather say "95% chance" instead of "while this 95% CI does not carry a 95% (aleatory) probability of containing the value, satisfied as I am with its assumptions and lacking other prior knowledge, it induces in me a 95% subjective probability it contains the value" every fucking time
1
12
1
reposted by
Thom Volker
With very large numbers of n’s you don’t need randomization, and with LLM’s we can generate very large numbers of n’s, so I think all of science is solved by now. I don’t see any problems with this.
13 days ago
5
96
19
With very large numbers of n’s you don’t need randomization, and with LLM’s we can generate very large numbers of n’s, so I think all of science is solved by now. I don’t see any problems with this.
13 days ago
5
96
19
I don't know, but publishing in a journal called "penis" might be a sign that the content shouldn't be taken too seriously
add a skeleton here at some point
13 days ago
0
6
1
reposted by
Thom Volker
econmaett
14 days ago
Does anyone know an example (paper, blog post) where frequentist and Bayesian methods lead to different conclusions?
#rstats
#stats
Or an anecdote that lead you to embrace one or the other approach?
14
44
8
Me, putting a strong prior on a Cohen’s d of 24: how so?
add a skeleton here at some point
14 days ago
1
3
1
reposted by
Thom Volker
Chelsea Parlett
14 days ago
- real sus that you want to require specific ID to vote and then immediately set precedent to instantaneously invalidate people’s ids - this also includes a “bounty” on trans people using the bathroom. Which is so disgusting I cannot even express how bad of an idea this is This is deeply alarming.
2
28
4
reposted by
Thom Volker
Chelsea Parlett
14 days ago
🚨hey so this is absolutely HORRIBLE for so many reasons I can’t even fully list out. But a few: - licenses are immediately invalid, making it difficult to even get around to change license or god forbid APPEAL THIS DECISION
loading . . .
Kansas revokes driver's licenses of hundreds of trans people, prompted by new law
Prompted by a new law, Kansas began sending letters to some trans people saying their drivers licenses were being invalidated until they change their gender information.
https://www.npr.org/2026/02/28/nx-s1-5728969/kansas-revokes-drivers-licenses-of-hundreds-of-trans-people-prompted-by-new-law
3
33
9
".. but Claude sa- "
add a skeleton here at some point
15 days ago
0
5
3
It is so clear that their words don’t bear any meaning. If you truly believe “radical left” is a security risk, and that a company is “radically leftist”, then would you really want your government to do business with this company?
add a skeleton here at some point
17 days ago
0
6
1
True! As a non-native speaker I’m always genuinely delighted when a reviewer remarks that a paper is well written (even when the paper is trashed afterwards)
add a skeleton here at some point
17 days ago
0
1
0
Coincidentally this gif is also an exact depiction of code in base R <ducks again>
add a skeleton here at some point
17 days ago
1
6
0
reposted by
Thom Volker
Cheryl Lynn Eaton
19 days ago
It's so ironic how often bigots talked about being "unpersoned" because people did not want to socialize with them. You know what's really an "unpersoning"? Having no driver's license in a rural area. Losing the one ID you need to vote or pay taxes or open a bank account.
3
713
178
Post a pic you took, no context, to bring some zen to the feed.
add a skeleton here at some point
17 days ago
0
5
2
python is better than R <ducks>
add a skeleton here at some point
18 days ago
4
13
2
reposted by
Thom Volker
Privacy International
18 days ago
Discord pausing its age verification rollout emphasises what privacy advocates have been saying about the technology: it creates a honeypot for malicious individuals, with no guarantees for users that the company they’re uploading their face to is safe.
privacyinternational.org/news-analysi...
loading . . .
Discord pushes back age verification after security risks revealed
Discord’s halted rollout exposes the inherent privacy risks of biometric and ID‑based checks.
https://privacyinternational.org/news-analysis/5737/discord-pushes-back-age-verification-after-security-risks-revealed
1
6
6
Unrelatedly, this is also how I picture the current US strategy to public health
add a skeleton here at some point
18 days ago
0
0
0
reposted by
Thom Volker
404 Media
19 days ago
The creator of the AI agent “Einstein” wants to free humans from the burden of academic labor. Critics say that misses the point of education entirely.
loading . . .
What’s the Point of School When AI Can Do Your Homework?
The creator of the AI agent “Einstein” wants to free humans from the burden of academic labor. Critics say that misses the point of education entirely.
https://www.404media.co/whats-the-point-of-school-when-ai-can-do-your-homework/
80
590
391
This is by far the dumbest take I’ve read today, which is quite an accomplishment after the State of the Union address. If you really think the point of school is to do production labour, I’ll advise you to, well, get back to school.
add a skeleton here at some point
19 days ago
0
1
0
Load more
feeds!
log in