Sam Hillman

Really excited to finally share that I'll be starting my @e3dtp PhD in September with @amybpedersen up in Edinburgh, where I'll be working on the ecology of infection and immunity in wild mice and get more opportunities to work on all things parasite-y!

@arthur_spirling They still come and get you for their pound of flesh after you emigrate too, if you have any plans of ever returning to the UK

The UK appears to be combining a world class undergraduate education system with a (uniquely?) brutal post-university existence for high skill workers. Not hard to see why Nick, 22 ans, might emigrate.

⚡️NO TENIM LÍMIT⚡️ Diumenge, a la FM de Sarrià, vam fer història! 🔸️4pd4, 5d7, 2d7, id4d8, 4d8, 2pd5 i pd4bal Som la primera colla del món casteller que descarrega 2d7 i 4d8 per primer cop a una diada💪 Celebrem-nos, colla, això només acaba de començar! #enVolemMés #castells

La meva colla ❤️

Boooofff

A QUARTA RONDA DESPRÉS D'UN id: PRIMER 4D8 DESCARREGAT DE LA NOSTRA HISTÒRIA 🫠🫠🫠🫠🥰🫠🥰🫠🥰🙃😅🥲😍 #enVolemMés #castells #castellers

Ja no cal dir res més, després de l'assaig d'ahir el sostre ens el posem nosaltres 🤯 Feinada espectacular, ens veiem diumenge a plaça per petar-ho 💥 #enVolemMés

How I spent my first La Mercè

De tot el que ens dona Sarrià, EN VOLEM MÉS!

@PidginPosting Agreed

@SamHillman Not much sympathy from me. I don’t think Hackneys should be allowed to use bus lanes anyway. And the tint thing is a safety requirement.

What are Edinburgh private hire drivers protesting about today? Big stream of them blasting their horns through Corstorphine.

@instrumenthull @seanluomdphd @anonymoostafa Isn't one of the points here we can't rely on law of large numbers? In some phase II oncology trials we might be looking at tens to low hundreds of patients. In these scenarios this matters

@seanluomdphd @anonymoostafa Linearity is a red herring. If treatment assignment is random and the LLN kicks in, linear regression works regardless of what the "true" outcome model is

what the heck?

A model trained with a frequentist objective using i.i.d. observational train and validation data is almost surely converging to the non-causal model of the underlying data generating process. That is because using short cuts/spurious correlations leads to a lower loss than not, i.e. you are actually specifically incentivizing your model not to be causal. "Emergence" believers' core fallacy is the assumption the causal model would have the lowest error, and therefore better optimization would eventually converge to the causal model. The opposite is true - the best scoring model (per frequentist objective) is actually the one that is best at exploiting spurious correlations.

Latest paper from my previous role. Great team to work with.

@anileh2 @AlexJDeighton 7.3%

@AlexJDeighton What’s the interest rate on your loans? That sound insane.

Saw today that after 3 years working as a doctor, extra shifts, long weeks, the 9% of my salary that goes to student loan repayments hasn't made a dent and my student debt has grown by £15,000 😂

@TJCoats @AlexJDeighton I keep hearing that but it still really doesn't feel great to be paying an additional 9% tax of my post-tax earnings (I'm overseas) and not making a dent in the interest for the next 25 years compared to those who went to university a few years before I did.

@AlexJDeighton Martin Lewis has some advice about not looking at the size of the loan and thinking about it as a ‘graduate tax’ on earnings above £25k. blog.moneysavingexpert.com/2024/10/martin…

I am excited to share our new article published in BJS. In this study, we proposed a modified IPCW estimator for Kendall's rank correlation coefficient for survival and ordinal outcomes. doi.org/10.1093/bjs/zn…

@sib313 @premnsikka Paying 9% of my post-tax income (because I moved abroad for a job) is seriously damaging. Everyone seems fine calling it a graduate tax when they don't have to pay it, but I'm stuck paying a shed load of money for the next 28 years and it's getting a bit annoying

@premnsikka Uni fees act more like a graduate, income-dependent tax than a debt burden. The majority are never repaid. So, reforms the system, maybe. Abolish it, no.

Students in England graduate with average £53,000 debt. Total debt £266bn, up to 7.3% interest rate. Most European nations don't charge uni tuition fees, England does. People penalised for education, can't start family, business. Abolish uni fees. theguardian.com/education/2025…

#Statistics thought of the day: challenges and resources for analysis of high-dimensional data: hbiostat.org/hdata

Avui hem descarregat el nostre 30è 4d7 i el nostre 25è pd5!!! 🥇 Moltes gràcies a les colles per l'ajuda i als nostres incansables músics! 🥁 La setmana que ve més i millor 😊✨ #laCollaEtsTu #castells

For the new kids in back: If you hate statistics, you'll love my free lectures. Putting science before statistics, from basics of inference & causal modeling to multilevel models & dynamic state space models. It's all free, made with love and sympathy. youtube.com/playlist?list=…