Joe Bak-Coleman
@jbakcoleman.bsky.social
Research Scientist at the University of Washington based in Brooklyn. Also: SFI External Applied Fellow, Harvard BKC affiliate. Collective Behavior, Statistics, etc..
This exchange about the Meta election collaboration highlights how industry can manufacture doubt without corrupting scientists or creating any sort of conpsiracy. A small 🧵
www.pnas.org/doi/10.1073/...
www.pnas.org/doi/10.1073/...
Reply to González-Bailón and Lazer: Industry control and conflicts of interest in social media research | PNAS
Reply to González-Bailón and Lazer: Industry control and conflicts of interest in
social media research
www.pnas.org
November 19, 2025 at 1:57 PM
This exchange about the Meta election collaboration highlights how industry can manufacture doubt without corrupting scientists or creating any sort of conpsiracy. A small 🧵
www.pnas.org/doi/10.1073/...
www.pnas.org/doi/10.1073/...
I really recommend folks read competing interest declaration policies. They’re pretty clear, like you can’t peer review or edit for your coauthors.
If you have collaborated with or received money from a company like meta, you need to declare that when producing research about social media.
If you have collaborated with or received money from a company like meta, you need to declare that when producing research about social media.
November 18, 2025 at 11:28 PM
I really recommend folks read competing interest declaration policies. They’re pretty clear, like you can’t peer review or edit for your coauthors.
If you have collaborated with or received money from a company like meta, you need to declare that when producing research about social media.
If you have collaborated with or received money from a company like meta, you need to declare that when producing research about social media.
It’s gonna be funny when psychology declares victory over the replication crisis because the bots start answering as the researchers are hoping.
November 18, 2025 at 11:10 PM
It’s gonna be funny when psychology declares victory over the replication crisis because the bots start answering as the researchers are hoping.
Folks who make garbage can regressions tend to be very concerned about p-hacking.
the five genres of statistics are Descriptive, Predictive, Causal, Garbage Can Regressions, and P-Hacking
November 17, 2025 at 12:44 PM
Folks who make garbage can regressions tend to be very concerned about p-hacking.
This is a fantastic article about James Watson but mostly it’s master class in dispatching of ghouls in science. Often the problem isn’t just that they’re amoral but that their being a(im)moral makes them dangerously wrong in ways that have cascading externalities on our understanding.
"What James Watson got wrong about DNA"
By the great Sohini Ramachandran (@sramach.bsky.social) and your boy for The Boston Globe (@bostonglobe.com).
www.bostonglobe.com/2025/11/14/o...
By the great Sohini Ramachandran (@sramach.bsky.social) and your boy for The Boston Globe (@bostonglobe.com).
www.bostonglobe.com/2025/11/14/o...
What James Watson got wrong about DNA - The Boston Globe
The science he helped pioneer consistently undermines his view that genes determine everything about us.
www.bostonglobe.com
November 16, 2025 at 2:31 AM
This is a fantastic article about James Watson but mostly it’s master class in dispatching of ghouls in science. Often the problem isn’t just that they’re amoral but that their being a(im)moral makes them dangerously wrong in ways that have cascading externalities on our understanding.
Reposted by Joe Bak-Coleman
"What James Watson got wrong about DNA"
By the great Sohini Ramachandran (@sramach.bsky.social) and your boy for The Boston Globe (@bostonglobe.com).
www.bostonglobe.com/2025/11/14/o...
By the great Sohini Ramachandran (@sramach.bsky.social) and your boy for The Boston Globe (@bostonglobe.com).
www.bostonglobe.com/2025/11/14/o...
What James Watson got wrong about DNA - The Boston Globe
The science he helped pioneer consistently undermines his view that genes determine everything about us.
www.bostonglobe.com
November 14, 2025 at 4:50 PM
"What James Watson got wrong about DNA"
By the great Sohini Ramachandran (@sramach.bsky.social) and your boy for The Boston Globe (@bostonglobe.com).
www.bostonglobe.com/2025/11/14/o...
By the great Sohini Ramachandran (@sramach.bsky.social) and your boy for The Boston Globe (@bostonglobe.com).
www.bostonglobe.com/2025/11/14/o...
Post Malört ergo propter malört
November 15, 2025 at 5:37 AM
Post Malört ergo propter malört
Reposted by Joe Bak-Coleman
What usually gets lost in the focus on what an evil racist James Watson was is just how colossal of a dumbass he was and just how far he set the field back.
But @sramach.bsky.social and @cbo.bsky.social kept their eye on the ball.
But @sramach.bsky.social and @cbo.bsky.social kept their eye on the ball.
"What James Watson got wrong about DNA"
By the great Sohini Ramachandran (@sramach.bsky.social) and your boy for The Boston Globe (@bostonglobe.com).
www.bostonglobe.com/2025/11/14/o...
By the great Sohini Ramachandran (@sramach.bsky.social) and your boy for The Boston Globe (@bostonglobe.com).
www.bostonglobe.com/2025/11/14/o...
What James Watson got wrong about DNA - The Boston Globe
The science he helped pioneer consistently undermines his view that genes determine everything about us.
www.bostonglobe.com
November 15, 2025 at 4:19 AM
What usually gets lost in the focus on what an evil racist James Watson was is just how colossal of a dumbass he was and just how far he set the field back.
But @sramach.bsky.social and @cbo.bsky.social kept their eye on the ball.
But @sramach.bsky.social and @cbo.bsky.social kept their eye on the ball.
A corollary of this is that something can be normally distributed in the parameters but not necessarily in the data. Using the right link functions and model, you’d be surprised how much the normal distribution can do.
Confusing stats language:
The "linear" is linear regression means "linear in the parameters".
It does not mean "can only fit straight lines", and things like polynomials and splines can be included in linear models.
online.stat.psu.edu/stat501/less...
1/2
The "linear" is linear regression means "linear in the parameters".
It does not mean "can only fit straight lines", and things like polynomials and splines can be included in linear models.
online.stat.psu.edu/stat501/less...
1/2
November 14, 2025 at 1:29 PM
A corollary of this is that something can be normally distributed in the parameters but not necessarily in the data. Using the right link functions and model, you’d be surprised how much the normal distribution can do.
The Hitler genetic work is like an over the top hypothetical for the ethics of using onymous dna to diagnose post genetic conditions of deceased individuals.
November 14, 2025 at 12:13 AM
The Hitler genetic work is like an over the top hypothetical for the ethics of using onymous dna to diagnose post genetic conditions of deceased individuals.
Daily dose of Fred
November 12, 2025 at 3:02 AM
Daily dose of Fred
If only she’d left a diary detailing her thoughts and experiences.
You’ve got Bohr, Feynman, and Einstein on your advisor board? BFD. My kid slipped into Anne Frank’s DMs.
From thebullshitmachines.com/lesson-11-tr...
From thebullshitmachines.com/lesson-11-tr...
November 12, 2025 at 1:31 AM
If only she’d left a diary detailing her thoughts and experiences.
Little guy got a clean bill of health.
November 8, 2025 at 5:53 PM
Little guy got a clean bill of health.
Reposted by Joe Bak-Coleman
WOW a loggerhead shrike without intense heat distortion, what afind!
November 4, 2025 at 6:16 PM
WOW a loggerhead shrike without intense heat distortion, what afind!
November 5, 2025 at 1:15 AM
Reposted by Joe Bak-Coleman
The Biden administration worked hard to accomplish this new free IRS filing system. It’s astounding that one should have to pay fees in order to pay their taxes. But this rent seeking is entirely consistent with the economic policies of the current administration that benefit the most wealthy.
👀 Scoop: IRS Direct File, the free government-backed program that let you file your taxes for free, is dead.
IRS wrote to state tax agencies saying it would not be operational this coming tax season, per records I've obtained.
IRS Direct File: 2023-2025.
(Story from when the pilot launched.)
IRS wrote to state tax agencies saying it would not be operational this coming tax season, per records I've obtained.
IRS Direct File: 2023-2025.
(Story from when the pilot launched.)
IRS tests free e-filing system that could compete with tax-prep giants
The tax agency has quietly built its own prototype system for filing tax returns digitally and free of charge, according to current and former officials.
www.washingtonpost.com
November 4, 2025 at 10:50 PM
The Biden administration worked hard to accomplish this new free IRS filing system. It’s astounding that one should have to pay fees in order to pay their taxes. But this rent seeking is entirely consistent with the economic policies of the current administration that benefit the most wealthy.
It’s ok, he’ll just fund folks to say the election was p-hacked.
November 5, 2025 at 1:01 AM
It’s ok, he’ll just fund folks to say the election was p-hacked.
Reposted by Joe Bak-Coleman
sorry but mamdani and cuomo should have worn blue and yellow hats, respectively
November 5, 2025 at 12:24 AM
sorry but mamdani and cuomo should have worn blue and yellow hats, respectively
Giving at seminar at Princeton CITP today at 12:15 est. It’s live-streamed to feel free to tune in!
spia.princeton.edu/events/citp-...
spia.princeton.edu/events/citp-...
CITP Seminar: Scientific Barriers to Evidence-Based Tech Policy | Princeton School of Public and International Affairs
Twenty years after Facebook spread across college campuses, its effects on society remain heavily studied and poorly understood. Little consensus exists over whether it promotes or degrades mental hea...
spia.princeton.edu
November 4, 2025 at 3:14 PM
Giving at seminar at Princeton CITP today at 12:15 est. It’s live-streamed to feel free to tune in!
spia.princeton.edu/events/citp-...
spia.princeton.edu/events/citp-...
This paper claims to provide evidence offline networks matter more than online for voting preferences, but winds up mistaking noise for signal and seems to forget that some folks online are quite influential.
academic.oup.com/pnasnexus/ar...
academic.oup.com/pnasnexus/ar...
Physical partisan proximity outweighs online ties in predicting US voting outcomes
Abstract. Affective polarization and increasing social divisions affect social mixing and the spread of information across online and physical spaces, rein
academic.oup.com
November 4, 2025 at 1:24 PM
This paper claims to provide evidence offline networks matter more than online for voting preferences, but winds up mistaking noise for signal and seems to forget that some folks online are quite influential.
academic.oup.com/pnasnexus/ar...
academic.oup.com/pnasnexus/ar...
Best World Series ever. This is insane.
November 2, 2025 at 3:45 AM
Best World Series ever. This is insane.
Meet Fred! You’ll be seeing more of him….
November 1, 2025 at 6:27 PM
Meet Fred! You’ll be seeing more of him….
It’s more pernicious than this because you’re also testing if your model is a perfectly unbiased representation of the data generating process.
But here's, the thing, p values and significance become useless at such large sample sizes. When you're dividing the coefficient by the SE and the sample size is in the tens of thousands, EVERYTHING IS SIGNIFICANT. All you're testing is whether the coefficient is different than zero.
October 31, 2025 at 10:22 PM
It’s more pernicious than this because you’re also testing if your model is a perfectly unbiased representation of the data generating process.
A helpful heuristic for
me is to think of science a bit like data chain of custody. An llm synthesizing data, annotating it or summarizing it breaks the chain from, say, humans to your final statistical inference or graph.
me is to think of science a bit like data chain of custody. An llm synthesizing data, annotating it or summarizing it breaks the chain from, say, humans to your final statistical inference or graph.
the amount of academic research now using llms in research (synthetic data generation, to classify, annotate, or analyse large scale data, etc) is astounding. remember, just cus use of llms in research is becoming normalised does NOT erase the fact it degrades the research & undermine your results
October 30, 2025 at 10:19 PM
A helpful heuristic for
me is to think of science a bit like data chain of custody. An llm synthesizing data, annotating it or summarizing it breaks the chain from, say, humans to your final statistical inference or graph.
me is to think of science a bit like data chain of custody. An llm synthesizing data, annotating it or summarizing it breaks the chain from, say, humans to your final statistical inference or graph.
October 29, 2025 at 10:02 PM