Sorry to have missed it... hope all who could make it had a nice time catching up! And I look forward to hearing more about it all.

I'd be out of a job though.

well said.

I'm a little envious of the breadth and depth of topics you get to cover in your stats course. I always find myself having to keep going over the basics (y=bx+c) again and again.

Yeah, I hear your pain when it comes to running and keeping track of a lot of model variants.

In terms of efficiency, I think I read that Stan now has much faster support for some forms of accumulator models. Might be worth looking into.

I've finally found time to read the rest of it (and we plan on disucssing te paper in our journal club on Friday). One question I have is: why didn't you implement a multi-level version, so tht you can just fit one model per data set?

A bit like the Clarke et al (2025) JEP:Gen model?

So a + Delta indicates a negative change?

[or I'm just being dumb on a Monday]

I'd assume current - previous.

I'd assume it means angular difference?

Am I right?

Figure 1 from the paper. Econ: from 2008 to 2024, methods aiming for causal inference have increased, theoretical work has decreased. Psych: Mostly experimental or descriptive correlational work.

Just learned about this study looking at methodological trends in psych and econ over time: online.ucpress.edu/collabra/art....

Matches my perception well: Nobody in psych bothers to (explicitly) try causal inference unless they conducted an experiment, not a lot of theoretical work either.

I've been strugging to find good modern British TV. [So have started re-watching good British TV from 15 years ago].

[Saying that, I suspect that is true of my TV watching habits in general. I suspose I am getting old]

Three major research universities opt out of new Elsevier deal Complaints over ‘price increases’ and open access models spur UK institutions to walk away from offer from publishing giant, despite nationally negotiated agreement

And so it begins... 3 UK universities (Essex, Sussex & Kent) have just gone public about walking away from their Elsevier Read & Publish deals, despite Jisc's recently announced agreement. Expect to see more of these over the coming months. www.timeshighereducation.com/news/three-m... #OpenAccess

This is the best paper I have read in ages (disclaimer: I haven't finshed reading, so I may end up hating it).

I've been thinking a lot about very similar problems, so great to see somebody else doing all the hard work so I don't have to :)

1000 Hurts Psychophysics is a human-facing science with interventions arguably more robust than medicine.

Psychophysics is a human-facing science with interventions arguably more robust than medicine.

A lot of parallels with the current mess in the UK Universtity sector.

Seeing stories like this always cheer me up about my relatively unsuccessful career in academia. I think I had about 3 emails waiting for me.

I agree 100%. This would be a great first step. Is this position clearly articulated in the UCU page?

Has this point been made to parliment by anybody with a sizeable platform? Am I missing sensible op-eds in the FT? Does anybody in Labour view this as something they could do?

oh, I agree entirely.

But the pensioners say "they should go get an apprenticeship"

Or just work.

Has anybody offered up a good defense of the current UK university secor and how it can be stabalised?

The only solutions I can imagine are large increase in student fees (unfair, and punatitve on young people?); large increase in funding from government (seems unlikely), or drastic reform?

I agree entirely. I've had (older, richer) relatives tell me that "too many young people go to university". It takes a lot of self control to avoid going on full on rant mode.

Not looking forward to having to make small talk with such people over Christmas.

I am currently an ex-member - I got fed up of all the endless calls to strike. I don't see any hope of improvement in the sector until we get a government that values (higher) education.

Perhaps if the UCU shared their counter-proposal, it would encourage disillusioned ex-members (me!) to rejoin.

For starters, in the future, do we see our students as campus-based, or commuting (or online)? I don't mind which, but I'm pretty confident that trying to do both will please noone.

Where can I find the UCU's Future Plan and alternative (costed?) proposal?

Through the Night - Keith Jarrett's The Köln Concert in a new arrangement - BBC Sounds Quator Classica perform a new arrangement of Keith Jarrett's legendary concert.

This is fantastic.

www.bbc.co.uk/sounds/play/...

Urrgh. I just spent an hour trying to get tikz working with quatro. Frustrating partial success. I can make figures appear, but they look *really* ugly.

Maybe i know somebody who can help, as Claude.ai wasn't at all helpful.

One idea I've been thinking about is cutting grid approximation. I'm very unsure though. It would free up time (I only have 10 weeks!), the coding is a bit clunky, and it confuses students.

But if I cut grid approx, my lecture on Probability doesn't connect to anything.

Two takeaways: i) yes, your book and module is hard for most students. but ii) students will still find it a struggle even if you make it easier.

When I started teaching Bayes, I ran my module as a reading course based on your textbook. Since then, I have reduced the amount of content every year. Yet my current students still tell me it is their hardest module.

But, this doesn't work when our students lack the confidence to question the AIs (and who can blame them given the amount of marketting the tech companies are doing)

The AIs can give good advice on how they should be used:

While this isn't a huge surprise, what I find despressing is how confidently wrong the AIs still are. When asked, they even admit that they're wrong, and that they are likely damaging educational outcomes.