Stats For Bios
@statsforbios.bsky.social
Statistics for biologists, medics, statisticians. Anyone really. By Tim Lucas, lecturer in epi/stats.
£10k for data linkage and months of admin to get the data.
At some point, it really begins to feel like these open datasets are not actually accessible. These timeframes and costs only really work if you have a paper mill going where specific grants and extractions are fluid.
At some point, it really begins to feel like these open datasets are not actually accessible. These timeframes and costs only really work if you have a paper mill going where specific grants and extractions are fluid.
January 22, 2026 at 7:53 AM
£10k for data linkage and months of admin to get the data.
At some point, it really begins to feel like these open datasets are not actually accessible. These timeframes and costs only really work if you have a paper mill going where specific grants and extractions are fluid.
At some point, it really begins to feel like these open datasets are not actually accessible. These timeframes and costs only really work if you have a paper mill going where specific grants and extractions are fluid.
It's pretty confusing how sometimes loading an R package loads the inbuilt datasets and sometimes doesn't. library(survival) loads rotterdam. And then data(rotterdam) gives a warning that the data isn't found! Pretty odd behaviour all round. #RStats
January 19, 2026 at 4:10 PM
It's pretty confusing how sometimes loading an R package loads the inbuilt datasets and sometimes doesn't. library(survival) loads rotterdam. And then data(rotterdam) gives a warning that the data isn't found! Pretty odd behaviour all round. #RStats
"As I write, highly civilized human beings are flying overhead, trying to kill me."
Phwoar. Orwell has some great first sentences.
Phwoar. Orwell has some great first sentences.
January 17, 2026 at 9:47 PM
"As I write, highly civilized human beings are flying overhead, trying to kill me."
Phwoar. Orwell has some great first sentences.
Phwoar. Orwell has some great first sentences.
Very happy to support people applying for this fellowship if you want to do a masters in Medical Statistics and a year of research. www.nihr.ac.uk/career-devel...
www.nihr.ac.uk
January 16, 2026 at 1:40 PM
Very happy to support people applying for this fellowship if you want to do a masters in Medical Statistics and a year of research. www.nihr.ac.uk/career-devel...
Reposted by Stats For Bios
wikipedia turns 25 today! the last unenshittified major website! backbone of online info! triumph of humanity! powered by urge of unpaid randos to correct each other! somehow mostly reliable! "good thing wikipedia works in practice, because it sure doesn't work in theory" - old wiki adage
January 15, 2026 at 1:47 PM
wikipedia turns 25 today! the last unenshittified major website! backbone of online info! triumph of humanity! powered by urge of unpaid randos to correct each other! somehow mostly reliable! "good thing wikipedia works in practice, because it sure doesn't work in theory" - old wiki adage
Reposted by Stats For Bios
Our machine learning competition on forecasting depression is online! We'd love for as many people as possible to participate. Please share in your respective networks — thank you :).
www.staff.universiteitleiden.nl/announcement...
www.staff.universiteitleiden.nl/announcement...
Machine-learning competition on forecasting depression in young adults - Leiden University
After nearly 5 years of work, the research team led by Eiko Fried has finished data collection in the ERC-funded WARN-D project on building a personalised early warning system for depression. But just...
www.staff.universiteitleiden.nl
January 12, 2026 at 12:52 PM
Our machine learning competition on forecasting depression is online! We'd love for as many people as possible to participate. Please share in your respective networks — thank you :).
www.staff.universiteitleiden.nl/announcement...
www.staff.universiteitleiden.nl/announcement...
"I don’t know. I will just give you the general advice to ... simulate fake data from your model and then you can apply your statistical procedures to your simulated data and repeat the process to understand the statistical properties of your methods."
statmodeling.stat.columbia.edu/2026/01/10/m...
statmodeling.stat.columbia.edu/2026/01/10/m...
My general advice if you’re stuck on a problem understanding a model you’ve fit to data | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
January 12, 2026 at 10:24 AM
"I don’t know. I will just give you the general advice to ... simulate fake data from your model and then you can apply your statistical procedures to your simulated data and repeat the process to understand the statistical properties of your methods."
statmodeling.stat.columbia.edu/2026/01/10/m...
statmodeling.stat.columbia.edu/2026/01/10/m...
Chatgpt confidently telling me wrong things about latex code.
I do believe it can be useful. It just, so far, has not ever been useful to me.
I do believe it can be useful. It just, so far, has not ever been useful to me.
January 9, 2026 at 10:44 AM
Chatgpt confidently telling me wrong things about latex code.
I do believe it can be useful. It just, so far, has not ever been useful to me.
I do believe it can be useful. It just, so far, has not ever been useful to me.
Reposted by Stats For Bios
Statistical Rethinking 2026 Lecture B01 Multilevel Models is online. This is the first lecture of the "experienced" section, in which we start with multilevel models and venture into vast covariance spaces. Full lecture list still here: github.com/rmcelreath/s...
Statistical Rethinking 2026 - Lecture B01 - Multilevel Models
YouTube video by Richard McElreath
www.youtube.com
January 9, 2026 at 10:34 AM
Statistical Rethinking 2026 Lecture B01 Multilevel Models is online. This is the first lecture of the "experienced" section, in which we start with multilevel models and venture into vast covariance spaces. Full lecture list still here: github.com/rmcelreath/s...
Been working on time-series models for a while now, including methods based on Almon lags. Just found out she was a woman, and died really young. Well, cheers to you Shirley. en.wikipedia.org/wiki/Shirley...
Shirley Montag Almon - Wikipedia
en.wikipedia.org
January 8, 2026 at 4:09 PM
Been working on time-series models for a while now, including methods based on Almon lags. Just found out she was a woman, and died really young. Well, cheers to you Shirley. en.wikipedia.org/wiki/Shirley...
There's an argument that we keep moving the goalposts on artificial intelligence. This is almost certainly true. But also, I think the blame rests with people that put the goal posts in the wrong place in the first instance, not those who are moving them towards the correct position.
Something I haven't seen discussed much wrt is AI intelligent/conscious is the difference between always on a only responding to requests.
I don't have a thought-out thesis. But something that replies to your question and then sits dormant doesn't feel conscious.
I don't have a thought-out thesis. But something that replies to your question and then sits dormant doesn't feel conscious.
January 6, 2026 at 12:43 PM
There's an argument that we keep moving the goalposts on artificial intelligence. This is almost certainly true. But also, I think the blame rests with people that put the goal posts in the wrong place in the first instance, not those who are moving them towards the correct position.
Something I haven't seen discussed much wrt is AI intelligent/conscious is the difference between always on a only responding to requests.
I don't have a thought-out thesis. But something that replies to your question and then sits dormant doesn't feel conscious.
I don't have a thought-out thesis. But something that replies to your question and then sits dormant doesn't feel conscious.
January 6, 2026 at 12:40 PM
Something I haven't seen discussed much wrt is AI intelligent/conscious is the difference between always on a only responding to requests.
I don't have a thought-out thesis. But something that replies to your question and then sits dormant doesn't feel conscious.
I don't have a thought-out thesis. But something that replies to your question and then sits dormant doesn't feel conscious.
When I'm not logged in, my YouTube shorts is almost 100% AI fake prank/fails type videos. When I'm logged in it's mostly just kinda interesting clickbait-y stuff. Not quite sure what to conclude from that.
December 29, 2025 at 7:17 PM
When I'm not logged in, my YouTube shorts is almost 100% AI fake prank/fails type videos. When I'm logged in it's mostly just kinda interesting clickbait-y stuff. Not quite sure what to conclude from that.
Reposted by Stats For Bios
Here's my favourite example - I was looking for information about a researcher named Vors, at U of Sydney many years ago. I love how the LLM got stuck in the alphabet - exactly what you'd expect from next-token prediction!
December 29, 2025 at 2:17 PM
Here's my favourite example - I was looking for information about a researcher named Vors, at U of Sydney many years ago. I love how the LLM got stuck in the alphabet - exactly what you'd expect from next-token prediction!
More kids game design opinions. Just play battleships 7x7 instead of 9x9 or whatever the default is. It's way more fun (hits are fun, misses are boring).
December 26, 2025 at 3:38 PM
More kids game design opinions. Just play battleships 7x7 instead of 9x9 or whatever the default is. It's way more fun (hits are fun, misses are boring).
Apropos of nothing of course. How's everyone's Christmases going?
To the (many) game designers that make games for young kids where you steal each other's cards, please fucking stop it. It always causes an argument. It's clearly more bad feeling for the stealee than good feeling for the stealer. Just bad game design.
December 25, 2025 at 7:01 PM
Apropos of nothing of course. How's everyone's Christmases going?
To the (many) game designers that make games for young kids where you steal each other's cards, please fucking stop it. It always causes an argument. It's clearly more bad feeling for the stealee than good feeling for the stealer. Just bad game design.
December 25, 2025 at 6:59 PM
To the (many) game designers that make games for young kids where you steal each other's cards, please fucking stop it. It always causes an argument. It's clearly more bad feeling for the stealee than good feeling for the stealer. Just bad game design.
I used to make models that tried to look a bit like the real world. Now I rarely do that. Instead I make models that ask questions about the real world.
And this is reflected in a fundamental change in what interests me. My core interest now is "what sort of questions can be answered?".
And this is reflected in a fundamental change in what interests me. My core interest now is "what sort of questions can be answered?".
December 20, 2025 at 8:41 PM
I used to make models that tried to look a bit like the real world. Now I rarely do that. Instead I make models that ask questions about the real world.
And this is reflected in a fundamental change in what interests me. My core interest now is "what sort of questions can be answered?".
And this is reflected in a fundamental change in what interests me. My core interest now is "what sort of questions can be answered?".
"Church-Turing thesis, Theodore Roszak version: Computers are ridiculous. So is science in general."
From Gödel, Escher, Bach.
Think I can get behind this.
From Gödel, Escher, Bach.
Think I can get behind this.
December 20, 2025 at 8:18 PM
"Church-Turing thesis, Theodore Roszak version: Computers are ridiculous. So is science in general."
From Gödel, Escher, Bach.
Think I can get behind this.
From Gödel, Escher, Bach.
Think I can get behind this.
Reposted by Stats For Bios
The {spatialRF} R package is back from the dead 🧟
Version 1.1.5 🚑, now available on CRAN, patches issues introduced by recent API changes across several dependencies.
A development roadmap for the coming months is available here:: blasbenito.github.io/spatialRF/ar...
#rstats
Version 1.1.5 🚑, now available on CRAN, patches issues introduced by recent API changes across several dependencies.
A development roadmap for the coming months is available here:: blasbenito.github.io/spatialRF/ar...
#rstats
Development Roadmap
blasbenito.github.io
December 20, 2025 at 9:17 AM
The {spatialRF} R package is back from the dead 🧟
Version 1.1.5 🚑, now available on CRAN, patches issues introduced by recent API changes across several dependencies.
A development roadmap for the coming months is available here:: blasbenito.github.io/spatialRF/ar...
#rstats
Version 1.1.5 🚑, now available on CRAN, patches issues introduced by recent API changes across several dependencies.
A development roadmap for the coming months is available here:: blasbenito.github.io/spatialRF/ar...
#rstats
"the task of replacing a burnt-out light bulb may turn out to require moving a garbage bag; this may unexpectedly cause the spilling of a box of pills, which then forces the floor to be swept so that the dog won't eat the pills."
Glad to see Hal's lightbulb is in Gödel, Escher, Bach
Glad to see Hal's lightbulb is in Gödel, Escher, Bach
December 19, 2025 at 10:16 PM
"the task of replacing a burnt-out light bulb may turn out to require moving a garbage bag; this may unexpectedly cause the spilling of a box of pills, which then forces the floor to be swept so that the dog won't eat the pills."
Glad to see Hal's lightbulb is in Gödel, Escher, Bach
Glad to see Hal's lightbulb is in Gödel, Escher, Bach
Have intros in papers got a lot shorter? Trying to find a good example for a student and half the papers I'm looking at have an intro section that's 3 or even 2 paragraphs long.
December 19, 2025 at 4:28 PM
Have intros in papers got a lot shorter? Trying to find a good example for a student and half the papers I'm looking at have an intro section that's 3 or even 2 paragraphs long.
Reposted by Stats For Bios
I'll forever be reminded of this blog post 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
December 18, 2025 at 8:19 PM
I'll forever be reminded of this blog post blog.genesmindsmachines.com/p/if-your-ra...
My band released music. Metal/hardcore type stuff if you're interested. First song has catchiest chorus of any song from any band I've been in. Which makes me happy. open.spotify.com/album/255oBg...
Forget My Eyes
open.spotify.com
December 18, 2025 at 1:37 PM
My band released music. Metal/hardcore type stuff if you're interested. First song has catchiest chorus of any song from any band I've been in. Which makes me happy. open.spotify.com/album/255oBg...
I got a model with attention running in R (lots of help from chatgpt). Now to see what the smallest model/dataset that actually does something interesting is. All just play to help myself understand.
Really good explanation of attention in llms.
One bit it doesn't cover is how the different bits are learned from data.
www.adaptive-ml.com/post/attenti...
One bit it doesn't cover is how the different bits are learned from data.
www.adaptive-ml.com/post/attenti...
December 18, 2025 at 8:59 AM
I got a model with attention running in R (lots of help from chatgpt). Now to see what the smallest model/dataset that actually does something interesting is. All just play to help myself understand.