Dan Simpson

Anyway here’s a goat from an Amish dairy.

i'm not sure it’s that limited, tbh

Siri, this is insane. (Context: I just upgraded to the latest phone) I got a text message from our building manager about some other renter doing some bullshit in the common areas. I blurted out “wow” entirely involuntarily. Siri helpfully put a !! emoji reaction on the text. Absolutely fucking not

In which I discuss what is still an under-appreciated issue with (linear) mixed models if you want to only condition on the past. It's not inconsistency, but it's not *not* inconsistency notstatschat.rbind.io/2026/10/26/l...

As always with AI we need to ask: 1. Is AI good at this? 2. Should we use AI for this? People are often surprised not only by how hard it is to answer (1) but also by how (2) is a completely separate question than (1)!

First time as academic wifey a a conference and I have no patience for people who want to know who I am.

Why is this student so upset about the mushroom, though? What could it have done to make her protest across the whole continent

Reading the QTs it seems like most of these people moved to the UK, which... you know, play clown games, win clown prizes

Just in case anyone was wondering about citation metrics, the last time i meaningfully did research (in a “publishing papers” sense) was 2022.

Obviously we come to this place for footnotes, but let’s not neglect the headings.

I recently moved to TU Darmstadt (Germany) and am currently hiring PhD student through ELISS. https://ellis.eu/news/ellis-phd-program-call-for-applications-2026 If you interested, please apply and choose me as a potential advisor. Topics include Continual/Distributed/Federated/Active/Transparent […]

I am hiring! There are probably about ~12 people in the world who meet exactly what I'm looking for, so we're open to considering teaching a 13th person to do what I do provided they already have a strong background in Bayesian statistics (non-negotiable) docs.google.com/document/d/1...

Would like to one day be this iconic and petty

Gift link: www.theatlantic.com/politics/arc...

I spoke a bit about Matthew Shepard over the weekend in person to some folks, but I didn't want to let the anniversary of his death — October 12, 1998 — pass by without giving a moment to him and his memory here.

The thing they don’t tell you about a long distance relationship is how fucking clean your house is after they’ve visited (because it got cleaned real hard before they came)

We love to see it! Have been teaching her Sappho translations for years. Total boss.

Margaret Hamilton, the first female programmer hired to work on the Apollo project who ultimately led the 100-person team that guided Armstrong and Aldrin to a safe landing on the moon, dies at 90. www.nytimes.com/2026/10/07/o...

Past life things: sea surface temp is excruciatingly hard to measure well. The oceans are also a very slow process where it’s legitimately hard to predict what changing large-scale features can/will do. We are talking multi-decadal cycles. **Do not ask about the collapse of the gulf stream**

Why isn't this on every TV screen and not the fairy tale of killer robots

someone please come and collect @furioursus.dev because I can't with them 💀

'Statisticians learn hierarchical models as tools; nobody in a statistics seminar says, “This is a response to a 150-year-old problem in the foundations of probability.” And nobody in a philosophy seminar says, “The answer is lme4."' sudippaul.substack.com/p/partial-po...

This period of my life has taught me how important it is to make sure my attention is re-routed to specific activities. Not spiralling. Not doom scrolling. Random activity X that takes up all my time. (I’m also blessed with a job I like that is very demanding of my attention when I’m working.)

Specificity gets results.

I am also a bit skeptical that training on all the data in the universe is better than modeling and understanding signal processing (I also like that more).

Reproducibility packages are a communication tool more than anything else. I wrote a bit about this, in a seasonally appropriate post, once upon a time statmodeling.stat.columbia.edu/2019/11/13/w...

Open casket funeral? I don’t even want people looking at me when I’m alive

I love reading modern C++ code because there are so many ways to say “I can’t be fucked working out what type this is. You do it.” SOFT!