Joe Hilton
@joebhilton.bsky.social
Research fellow in mathematical modelling at the Manchester Centre for Health Economics. Not an economist, possibly a mathematician. Personal account. https://jbhilton.github.io/ https://research.manchester.ac.uk/en/persons/joseph-hilton
This is how I look when your data availability statement says "on request". Hate to resort to an appeal to emotion but you should not be putting me through this kind of stress.
KOTH Screens@kothscreens.bsky.social · 2d ago
Someone told me "Bluesky is just like Twitter." I argued that was untrue on the basis that last time I had a Twitter account most times I got a new follower their bio said "single & looking for fun" & here when I get a new follower it tends to say something like "professor of rare moths".
Something happening once doesn't mean it will happen again soon, and something happening once also doesn't mean it won't happen again soon.
Riley Bruce@rileybruce.bsky.social · 4d agoWhat’s a thing from your area of expertise (or special interest) that you think it would behoove everyone else to know?
Seeing a lot of eclipse posting and very little meteor shower posting. Really makes me question the taste of a lot of people I'm following here.
The thing that gets ignored here is just how utopian headphones and streaming would have seemed to someone living 100 years ago. Even if most people don't use it this way, the fact that you can listen to a Mahler symphony on the way to work genuinely is the stuff of early 20th century sci-fi.
The Guardian@theguardian.com · last wk.The hill I will die on: Remove those earphones – you’re blocking out the music of humanity | Stefan Stern
The way the bluesky science ecosystem puts every vaguely stats-adjacent academic into one big pool of stats posters really feels like a ploy to make me form an opinion on p values. It's getting harder but I remain resolute in my commitment to not having an opinion on p values.
CLOSING SOON: Postdoc (Coventry, UK) Infectious disease modelling and statistical methods for Neglected Tropical Disease elimination. with Emma Davis at University of Warwick More details: http://iddjobs.org/jobs/2566
So I think what happened here is BEAST assigned equal probability to Diddy Kong being DK Jr's son or grandson, but when you average out and drop the weights you end up with both options in the tree. This is exactly why you should perform uncertainty propagation rather than using consensus trees.
Brendel@brendelbored.bsky.social · 2w agoSaw this picture and trying to figure out the Diddy Kong situation is leading me down a rabbit hole that can only end with me rejecting the moon landing
What's fundamentally missing from the Odyssey discourse is any acknowledgement that Christopher Nolan is just too humourless to handle a story about a bunch of guys who get turned into pigs.
Continuing my ongoing investigation into how much probability theory old school RPG developers actually knew: just finished Dragon Quest I and it looks like the devs knew enough to avoid a geometric distribution on encounter timings, but still ended up with geometric status effect durations.
Austria is years, maybe decades ahead of us in the field of sausage roll development
I'm in Graz this week for #ECMTB26 and am presenting three (yes three!) things. I have a poster on Tuesday on mathematical biology in health economics, I'm talking on Wednesday about vaccine uptake patterns in the ONS Covid-19 Survey, and on Friday I'm speaking about spatial mapping of avian flu.
"Whether or not men should be routinely screened for prostate cancer seems simple enough to answer, but only on the face of it." In this Editor's Choice, @kamranabbasi.bsky.social writes on why not screening for prostate cancer is justified www.bmj.com/content/393/...
The UK Government has just published its Health Security Risk Assessment (HSRA) - this is a document to aid all sorts of organisations plan for threats, as it says not intended for individuals, but it should probably be better known about. www.gov.uk/government/p...
Health Security Risk Assessment (HSRA): 2025 edition
gov.uk
Real-life conspiracy theory: the people writing probability distribution libraries are militant frequentists who intentionally make specifying lognormal parameters a baffling ordeal so that no one can ever get their priors right.
Less than 1 week to apply for this postdoc! If you want to find out more about the project have a look at our recent preprint: www.biorxiv.org/content/10.6... #mevosky
biorxiv.org
Michael Brockhurst@brockhurstlab.bsky.social · 4mo agoWhy does antibiotic resistance evolution vary between patients? Come to @officialuom.bsky.social @mermanchester.bsky.social to help us find out! 2.5 year @wellcometrust.bsky.social postdoc position in experimental evolution Closing 15 May. Apply here: www.jobs.manchester.ac.uk/Job/JobDetai...
For reasons that are certainly unrelated to grant applications, does anyone know of (ideally with some evidence) uses of tools I have contributed to (scoringutils, epinow2, epinowcast, epidist, primarycensored, episoon, epinow, censoreddistributions ...) from different parts of the world?
This podcast is very important to me because it's the only one I listen to that overlaps with my research interests enough for me to be annoying about it at work instead of just at home.
Aubrey Gordon@yrfatfriend.bsky.social · 4mo ago@maintenancephase.bsky.social is on here now!
Guy inventing 2FA: Yes so to start a day's work on the second most distracting thing humans have invented, I'll just need you to momentarily divert your attention to the first most distracting thing.
Really pleased with how this one has come out. We take common output formats for household-based field epi studies, see how much structure we can impute from them, and make the case for reporting case and contact numbers stratified by household size.
Thomas House@tah-sci.com · 5mo agoNew Preprint! "Bayesian Inference for Epidemic Final Size Datasets with Hidden Underlying Household Structure" - with @joebhilton.bsky.social, @joebr22.bsky.social and Lorenzo Pellis. arxiv.org/abs/2603.25235
1/ 🎤 Today's @juniper-network.bsky.social seminar talk was by Matthew Ryan on "Sometimes BaD modelling is a good idea" 💻 Behaviour and disease (BaD) models: Allow for adaptive human response to intervention uptake & abandonment governed by psychological factors (e.g. perception of illness threat).
Seminars | Juniper
We run a virtual weekly seminar series on a Wednesday 14:00-15:00 (UK time) during academic term-time. The aim of the seminars is to provide an informal environment for researchers working at the inte...
juniper.maths.org
Another classic "we know British people are doing these puzzles and we do not care" installment of Strands today. I feel like I am solving a wordsearch in a dream and my subconscious mind can't reliably stick to a theme.
Playing the Pokémon Leaf Green rerelease and I am now fully convinced no one involved knew what a geometric distribution was. "Just draw a random number every time the player presses a button. This will surely make for satisfying gameplay."