10 years of doing applied stats and I've still only seen like 1 regularity condition in that time. Those mild freaks are hiding out there in large numbers waiting to strike.

It helped me during my PhD where there was a risk I might develop a Bayesian superiority complex (of a certain philosophical kind). I still think of the phrase "take the posterior seriously" and I'm writing papers this year that do this. So one fan in the UK anyway!

Estimating group fixed effects in panel data with a binary dependent variable: How the LPM outperforms logistic regression in rare events data Estimating fixed effects models can be challenging with rare events data. Researchers often face difficult trade-offs when selecting between the Linea…

Shocked to see papers like this:

www.sciencedirect.com/science/arti...

I see this kind of thing as downstream of thinking that statistics is an "in situation X, I must use tool Y" type of discipline. So they do 'tests' to 'check the tool is the right one' and there can be only one right tool.

You have to imagine this in an Irish accent but the phrase I use is "Who'll be lookin' at ye?" that I stole from an Irish friend's Mum. Something about the accent really makes it land for me.

Not my wheelhouse but this does look really interesting. I'd be coming at it from a producer of statistics angle but this stuff is really important to know about. Statistics is never done in a vacuum.

This is similar to how I feel about the research that tries to estimate the effect on happiness of becoming a parent. When I read it I think it's confused from the outset. Not my area though so I don't hold this strongly but I'm getting confirmation bias reading this thread.

I enjoyed that. Ive attended some Quaker meetings and enjoyed it, although I am not a member. I think they would say they aren't so much anti-clerical as they are anti-laity since they view it as abolishing the laity rather than the clergy since absolutely anyone can stand and minister.

I know this is a serious post but it's giving me Blinded by the light vibes.

The authoritarian libertarians met the equestrian millenarians to see if it was safe to go outside.

Or something. It's 4 am here I dunno

I agree. It's why in such a huge fan of Marcus Aurelius' Gettin' Stuff Done.

Back in the drawer the LLM goes. Would have been 10x faster to write it myself.

I remain an LLM user only using it as a kind of google search, where the aim is to as quickly as possible leave the land of hallucinations and read things for myself.

I just tried to use google gemini (plus) to help me with some coding.

I gave it a .tex file with an outline of a toy simulation I want to run. This simulation is very simple but gemini has repeatedly failed to generate correct code. Every error 'solved' creates 2 new ones.

I never remember to add these bloody things #StatsSky

If you've noticed a common mistake in the literature and you have a nice way of explaining why it's a mistake but don't have a solution, what should you do?

Is it worth a paper? What kind of paper? I'm imagining the academic equivalent of a blog post. Is that a thing?

This is fun. I just used it to back of the napkin the benefits of moving some finances around that I'm planning on doing this week. Very intuitive interface

Surely there are some kinds of unacknowledged bias that means "the main point" is weakened to the point of being almost useless?

Wait ...I need Karla to lose? Okay Picard as Karla has to lose but make it look like it's close so everyone maintains respect for everyone else and the federation can come into existence

If Karla wins then the west falls then the warp drive is invented by a russian instead and it becomes a tool for authoritarian oppression leading to an alternative future where the federation is EVIL

If it's nominated for the man booker it's a mark against. My partner doesn't get why. I say "they are trying way too hard to be clever"

Kinds of thoughts I have when I haven't slept well. I'm going to put my phone down

Cf why I hate "rational" Vs "emotional" thinking, like that's a real distinction. Mate, you love the feeling you have when you think you are being logical. It's emotions all the way down.

A lot of my philosophical disposition is based on deep emotion. I feel like this isn't talked about enough. Why isn't it valid to just say it feels right to think certain things and if you have a different emotional world then you'll probably think something different.

Reflecting today on how I ended up interested in statistics and finding myself being a kind of instrumentalist.

Big part of it was spending my early 20s using maths as a form of self soothing. And then at some point it stops working for that because you ask too much of the maths.

And it's getting smaller! I see explicit advice like "unless you really know what you are doing, just use stan" etc. (And I mostly agree with that - but sometimes you have to go it alone)

A screenshot of a paragraph from a piece of writing about statistics that reads: When the international community of physicists agreed on the statistical analysis they would perform on the data they collected at the Large Hadron Collider, they were doing statistics. But when they agreed what the conditions were for declaring the Higgs boson real or not, they were not really doing good statistics anymore. They were agreeing a position as a scientific community about when and how to leave an uncertain world and enter a new world with one new piece of certainty attached to it. The statistical work was one (small) piece of this decision making process. This community-driven process, viewed as a whole, should not, in my view, be seen as a part of statistics, though I understand that it looks like it could be. I should be really explicit here and emphasise that saying something is not statistics is not the thing same as saying that it is bad science.

Trying to write about "good statistical practice" and applying statistics to models with immense predictive power is the final boss.

I feel like this is a weird place to draw a line but I have to draw it here to be consistent with my opinions on messier applications of stats.

#statsky

Scientists actually created a device called Kissenger that lets people physically "kiss" each other through their phones, transmitting real lip pressure across the internet in real time.

feel like they might want to rethink the name

Never seen this before. Every time he named a car was a coin flip whether he'd crack or not. Gave me a good chuckle

Trying to blow the 5yo's mind by suggesting she cannot tell for sure if she is growing or if everything in the universe is shrinking except for her. She's having none of it though. She is smarter than many philosophers it would appear

PSA if you are typing quickly and want to type

xoxoxo

please be aware that these letters are close on the keyboard to a bunch of other letters and autocorrect may replace this loving sign off with

cockcock

Just something to be aware of. Definitely didn't just happen to me.

Economics has failed on the climate crisis. This complexity scientist has a mind-blowing plan to fix that Doyne Farmer says a super-simulator of the global economy would accelerate the transition to a green, clean world

www.theguardian.com/environment/...

A smidge of hubris in the air today

But has he reviewed the Heinz boil-in-a-tin sticky toffee pudding? I shall reserve judgement until then