iiinova — where your digital self keeps evolving

Stats For Bios @statsforbios.bsky.social · 29/09/2026

Why does windows default to not showing file extensions? So stupid. And a really nice way to make teaching into R more difficult. #RStats

050

Reposted by Stats For Bios

Rod Page @rdmpage.bsky.social · 23/09/2026

Jobs galore at @nhm-london.bsky.social @dissco.bsky.social - jobs.nhm.ac.uk/Job/JobDetai... - jobs.nhm.ac.uk/Job/JobDetai... - jobs.nhm.ac.uk/Job/JobDetai... - jobs.nhm.ac.uk/Job/JobDetai... - jobs.nhm.ac.uk/Job/JobDetai... including Heads of Digitisation and Technical Innovation

jobs.nhm.ac.uk

DiSSCo UK Digitiser:South Kensington

0412

Reposted by Stats For Bios

Saganism @sagan.bsky.social · 22/09/2026

A humbling reminder from Carl Sagan: Even if you read 1 book a week for your entire life, you'd only scratch the surface of human knowledge.

221138296

Reposted by Stats For Bios

MC Stan @mc-stan.org · 17/09/2026

Release of CmdStan 2.40, including new Stan Math, core Stan, and Stanc, is now available! Blog post with new features blog.mc-stan.org/2026/09/16/r... Highlights - integrate_1d_double_exponential, a variadic version of old integrate_1d - integrate_1d_gauss_kronrod, a different quadrature rule ...

blog.mc-stan.org

Release of CmdStan 2.40

We are very happy to announce that the 2.40.0 release of CmdStan is now available on Github! As usual, the release of CmdStan is accompanied by new releases of Stan Math, core Stan, and Stanc3. Thi…

13016

Stats For Bios @statsforbios.bsky.social · 17/09/2026

Had a great week teaching Geospatial Models for Public Health at Tanzanian National Bureau of Statistics. Been supporting Janine Illian teaching inlabru and teaching disagapp for disaggregation regression. inlabru-courses.github.io/Tanzania_202... Now get the train back to Dar es Salaam

View from train from Dar es Salaam to Dodoma.

130

Stats For Bios @statsforbios.bsky.social · 16/09/2026

Reminder that "wiggly" is absolutely a technical statistical term. No discussion needed.

23111

Reposted by Stats For Bios

Stats For Bios @statsforbios.bsky.social · 11/09/2026

Preprint shinyapp by @simonsmart.bsky.social here. User-friendly, reproducible software for high-resolution predictions from aggregate polygon case counts (or other data). Once you're done, click a button to get a Rmd file out. #RStats #DiseaseMapping #malaria www.medrxiv.org/content/10.6...

054

Reposted by Stats For Bios

Francisco Rodriguez-Sanchez @frodsan.bsky.social · 11/09/2026

This paper is 20 years old but keeps being as relevant today as back then :/ doi.org/10.1111/j.13... #statistics #ecopubs

Why do we still use stepwise modelling in ecology and behaviour?

The principal drawbacks of stepwise multiple regression include bias in parameter estimation, inconsistencies among model selection algorithms, an inherent (but often overlooked) problem of multiple hypothesis testing, and an inappropriate focus or reliance on a single best model.

1224

Reposted by Stats For Bios

Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 10/09/2026

Modeling non-response is an example I like to use when arguing that "descriptive" statistics also require causal inference. To describe the population, you have to model what causes the sample. Similar to occupancy modeling in ecology in many ways.

110119

Stats For Bios @statsforbios.bsky.social · 11/09/2026

054

Stats For Bios @statsforbios.bsky.social · 10/09/2026

My bar for genAI has been for a while "I'll consider it useful when it can fill in a form for me". Copilot, with a lot of prompting and nonsense, filled 90% of a form for me. That's it, I'm in.

010

Stats For Bios @statsforbios.bsky.social · 09/09/2026

The YouTube android app is just so much worse than the mobile webpage. And I can't delete it.

010

Reposted by Stats For Bios

Aki Vehtari @avehtari.bsky.social · 08/09/2026

I'm looking for doctoral students, postdocs and research fellows to work with on Bayesian Workflow. Flexible starting time

02115

Stats For Bios @statsforbios.bsky.social · 08/09/2026

Say I've got a train dataset and a test data set. I fit a linear model to the train set and evaluate within-sample error. Then I fit the linear model to the train set and evaluate with the test set (i.e. cross validation). The 2 models are identical and equally overfit. The metric is different.

192

Stats For Bios @statsforbios.bsky.social · 08/09/2026

I've probably moaned about this before. Cross validation doesn't control overfitting (your model is still just as overfit). It (tries to) estimates predictive performance without being tricked by overfitting. Big difference.

191

Reposted by Stats For Bios

Visruth Srimath Kandali @visruth.com · 01/09/2026

`stanflow` v0.2.0 is out! `stanflow` is a metapackage a la `tidyverse` to provide a convenient way to install and manage #rstats Stan packages. The package is still in early stages; as such, if you want some features they can probably be added! Stan forum: discourse.mc-stan.org/t/stanflow-v...

discourse.mc-stan.org

`stanflow` v0.2.0 is out

It’s been a while, but stanflow v0.2.0 has just been released by @Visruth. stanflow is a metapackage a la tidyverse to provide a convenient way to install and manage R Stan packages. (See Soft relea...

0166

Reposted by Stats For Bios

Dave Hemprich-Bennett @davehb.bsky.social · 02/09/2026

It's pretty wild to see how much the air quality has improved in the areas of London I frequented before I left. Looks like NO2 is now ~1/4 of what it used to be at my old uni when I started there. Fantastic stuff

082

Stats For Bios @statsforbios.bsky.social · 01/09/2026

Playing around with my Goodreads data. lm(My.Rating ~ Number.of.Pages + Year.Published + Author.Reads + Year.Added) Author.Reads is how many books by that author I've read. Anyone wanna play guess the R^2 or guess sign and sig of variables? #RStats

120

Reposted by Stats For Bios

Francisco Rodriguez-Sanchez @frodsan.bsky.social · 01/09/2026

Great collection of Shiny apps (and R package) for #teaching #ecology. Apps come in different languages (including Spanish) ecoevoapps.gitlab.io

Partial list of Shiny apps designed for teaching ecology, hosted at https://ecoevoapps.gitlab.io/

02418

Reposted by Stats For Bios

medRxivpreprint @medrxivpreprint.bsky.social · 18/06/2026

Accounting for Human Movement to Improve Exposure-Health Models www.medrxiv.org/content/10.64898/20…

001

Stats For Bios @statsforbios.bsky.social · 28/08/2026

Wanted to know how many unhidden slides I had in my ppt deck. Found a useful solution (right click the file, properties. has slides and hidden slides). The solution is given in such a smug way though! Duh, just look in the file properties. learn.microsoft.com/en-us/answer...

learn.microsoft.com

how to count unhidden slide in power point 365 - Microsoft Q&A

how to count unhidden slide in power point 365?? still use VBA ?

100

Reposted by Stats For Bios

Stats For Bios @statsforbios.bsky.social · 25/08/2026

Reread my blog post on the biggest problem in statistics. On re-read, I still don't think it is terrible (other than the typos and things). So I'll repost. timcdlucas.github.io/the-biggest-...

timcdlucas.github.io

The Biggest Problem In Statistics

03916

Stats For Bios @statsforbios.bsky.social · 28/08/2026

Using a causal lens to help understand spatial models. No maths. Particularly relevant to spatial epidemiologists and species distribution modellers. But others as well. timcdlucas.github.io/spatial_mode... #SDM #malaria #GIS #episky #CausalInference

timcdlucas.github.io

Spatial_models_with_a_causal_lens

252

Stats For Bios @statsforbios.bsky.social · 26/08/2026

"Laughter has dug more useful tunnels all by itself than all the tears on earth." Cortázar - Hopscotch Not sure if I agree but I like it nonetheless.

000

Reposted by Stats For Bios

Stats For Bios @statsforbios.bsky.social · 07/08/2026

Estimating the effect of short term (hourly) air pollution is difficult but that's what we tried to do here. We used data that, unusually, has admission time. We found significant associations between NO2 and asthma admission at 3-6 hour lags but not other lags. bmjopen.bmj.com/content/16/8...

The relative risk (RR) of emergency hospital admissions associated with mean nitrogen dioxide at the specific lags from 0 to 24 hours. Note: the red line shows the average RR of emergency hospital admissions for acute asthma, and the error bars are the 95% CIs.

Lags between 0 and 2 hours are insignificant, with large uncertainties at 0 hours. Lags between 3 and 6 hours are significantly positive, with CIs around 1,005 and 1.04. After 6 hours, all CIs cover zero again.

101

Stats For Bios @statsforbios.bsky.social · 25/08/2026

Reread my blog post on the biggest problem in statistics. On re-read, I still don't think it is terrible (other than the typos and things). So I'll repost. timcdlucas.github.io/the-biggest-...

timcdlucas.github.io

The Biggest Problem In Statistics

03916

Reposted by Stats For Bios

Shikhara Bhat @shikharabhat.bsky.social · 20/08/2026

Some birds from Sabah to brighten your timeline

0131

Stats For Bios @statsforbios.bsky.social · 13/08/2026

Album of the week. A black metal (blackgaze really) album about Bill the Pony. I mean look at that cover.

A cute cartoony illustration of Bill the Pony.

050

Stats For Bios @statsforbios.bsky.social · 07/08/2026

101

Stats For Bios @statsforbios.bsky.social · 05/08/2026

Anscombe, who invented the Anscombe quartet, is from Hove (actually)! Didn't realise he was from so close to me.

110

Stats For Bios @statsforbios.bsky.social · 05/08/2026

Dear people familiar with American education. At college level, does "freshman" only refer to undergraduates? Or can you also be a freshman grad student? Just reading a book and don't quite understand.

120

Reposted by Stats For Bios

Priscilla Lau @prilau.bsky.social · 30/07/2026

Our paper (also, my first first-author paper) is now available in MEE early view! In this study, we introduced a state-dependent Ornstein-Uhlenbeck model we implemented in RevBayes to test adaptive hypotheses in macroevolution. (1/3) besjournals.onlinelibrary.wiley.com/doi/10.1111/...

besjournals.onlinelibrary.wiley.com

An efficient Bayesian phylogenetic approach for joint inference of continuous and discrete trait evolution under a state‐dependent Ornstein–Uhlenbeck model

Macroevolutionary adaptation of a continuous trait to different discrete states across species can be modelled using a phylogenetic state-dependent Ornstein–Uhlenbeck (OU) process. Existing infere...

27841

Stats For Bios @statsforbios.bsky.social · 28/07/2026

Read some news about how crap social media is. Just endless adverts with no actual social component. But bluesky isn't like that! It's not a million-post-a-second fart of content, but what is here is pretty good, and social. So thanks for having me!

031

Stats For Bios @statsforbios.bsky.social · 23/07/2026

Hey, someone that actually understand exponentials. Pretty rare on the internet it seems.

000

Stats For Bios @statsforbios.bsky.social · 23/07/2026

The aching amplitudes that set our needles all a-flickering.

020

Stats For Bios @statsforbios.bsky.social · 21/07/2026

Having different working directories for different chunks, and being tied to the script and stuff, is all just a mess. It used to work totally fine. You set the working directory. If you needed to change, you changed.

230

Stats For Bios @statsforbios.bsky.social · 20/07/2026

Dear outlook. ctrl+r in the browser means refresh. Don't just override stuff that everyone knows! I'm renaming this account to "Old man yells at clouds for biologists". New logo in the works.

021

Stats For Bios @statsforbios.bsky.social · 20/07/2026

UKRI, uninvited resubmissions are no longer accepted. BBSRC: Over 50% of objectives or work packages must be entirely new. Soooo, you spend a month (more) working on it, roll the dice once, and throw half of it in the bin if you get unlucky? This seems a really good way to increase wasted time.

150

Stats For Bios @statsforbios.bsky.social · 16/07/2026

Ethan is just 5x better at being a food YouTuber than everyone else. Your dish is missing YouTube pedagogy. www.youtube.com/watch?v=aj8q...

youtube.com

5 simple questions that will ACTUALLY make you better at cooking.

YouTube video by Ethan Chlebowski

000

Stats For Bios @statsforbios.bsky.social · 14/07/2026

Grant submitted and France out. Vamoos.

100

Stats For Bios @statsforbios.bsky.social · 14/07/2026

Ideally applied data analysts doing research as well... Think about your question Think about your estimand Think about your study design Think about your dag Then write 1-10 lines of R code to data clean and fit an appropriate model.

011

Stats For Bios @statsforbios.bsky.social · 14/07/2026

King for a day. All software must default to pasting without formatting. You can have a hotkey for pasting with formatting if you like. But ctrl + v is pasting without formatting everywhere forever all the time.

151

Stats For Bios @statsforbios.bsky.social · 09/07/2026

Wrote a quick post on what I think the biggest open problem in statistics is. tldr every analysis has 10-20 medium important, medium difficult-to-fix issues. In practice we can account for 1 or 2 but not 10-20. Lots of typos. Just starting some chat. #StatsSky timcdlucas.github.io/the-biggest-...

timcdlucas.github.io

The Biggest Problem In Statistics

030

Stats For Bios @statsforbios.bsky.social · 09/07/2026

Jeez the textedit app on Mac is a pain in the arse. It is desperate for my files to be RTF and just changes .md files to .rtf and adds a bunch of crap into them to make that work. I need to find something simpler and cleaner.

340

Stats For Bios @statsforbios.bsky.social · 01/07/2026

Happened again. I don't know if it's some Mac vs windows thing, or something to do with windows refusing to save over files. But fuck it. Never commenting on a pdf ever again.

000