iiinova — where your digital self keeps evolving

Reposted by James Azam

CMMID @cmmid-lshtm.bsky.social · 06/08/2026

📊 Working in #InfectiousDisease modelling? It’s your last chance to apply for our @lshtm.bsky.social short course: Model Fitting and Inference for Infectious Disease Dynamics Running from 7-10 Sept 2026 #PublicHealth Apply by 23:59 BST on 7 August 🔽 www.lshtm.ac.uk/study/course...

156

Reposted by James Azam

Sam Abbott @seabbs.bsky.social · 22/05/2026

Estimating the current size of the 2026 DRC Bundibugyo virus outbreak: a joint Bayesian re-analysis of the McCabe et al. report w/ @kathsherratt.bsky.social Sam Brand and @sbfnk.bsky.social

22915

Reposted by James Azam

Adam Kucharski @adamjkucharski.bsky.social · 06/05/2026

"Based on the dataset you shared, US and UK responses differ mainly in tone, intensity, and wording style, even though they express similar emotional states" New post on what happened when I got Copilot to do some data analysis: kucharski.substack.com/p/real-signa...

kucharski.substack.com

Real signals or artificial stereotypes?

Adventures with a cultural Copilot

15338142

James Azam @jamesazam.bsky.social · 20/10/2025

Bayesian Data Analysis Primers/Tutorials I gathered these primers for learning bayesian data analysis, mainly for myself but I hope they are helpful to you too. If you know of similar articles, do share them in the comments. #bayesiananalysis #datascience #machinelearning #rstats #python

1257

Reposted by James Azam

Sam Abbott @seabbs.bsky.social · 17/10/2025

#epinowcast 0.4.0 is out! This release has been a long time coming and contains work from many contributors. It includdes new features, better better and clearer documentation. package.epinowcast.org/news/index.h...

package.epinowcast.org

Changelog

1107

Reposted by James Azam

Thomas Lin Pedersen @thomasp85.com · 11/09/2025

I am beyond excited to announce that ggplot2 4.0.0 has just landed on CRAN. It's not every day we have a new major #ggplot2 release but it is a fitting 18 year birthday present for the package. Get an overview of the release in this blog post and be on the lookout for more in-depth posts #rstats

tidyverse.org

ggplot2 4.0.0

A new major version of ggplot2 has been released on CRAN. Find out what is new here.

9851281

James Azam @jamesazam.bsky.social · 13/09/2025

My go-to resource for scientific writing The Writing Tips Series by the Journal of Clinical Epidemiology is hands down one of the best guides for academic writing: www.sciencedirect.com/special-issu... (1/3) #AcademicWriting #Research #PhDLife #ScientificWriting #Masters #PhD #AcademicChatter

130

James Azam @jamesazam.bsky.social · 13/09/2025

A developer's love language.

010

Reposted by James Azam

Sam Abbott @seabbs.bsky.social · 09/06/2025

The other major addition in this release is lovely new stan docs thanks to @jamesazam.bsky.social primarycensored.epinowcast.org/stan/group__...

primarycensored.epinowcast.org

primarycensored: Primary Censored Distributions Functions (Vectorized)

021

Reposted by James Azam

Jiaxin ZHOU @jiaxinz.bsky.social · 11/07/2025

Back from Kenya, where I had the privilege of co-leading an Outbreak Data Science workshop with @jamesazam.bsky.social at KEMRI-Wellcome Trust. I'm proud to see open, reproducible tools like #EpiverseTRACE @epiverse-trace.bsky.social making a difference.

075

Reposted by James Azam

Sam Abbott @seabbs.bsky.social · 15/05/2025

Just been looking at deepwiki as a way of summarising packages/presenting more interactive documentation via chatting to an LLM. On the face of it seems really useful (though as normal small errors here an there) Thanks @jamesazam.bsky.social for the headsup!

deepwiki.com

epinowcast/epidist | DeepWiki

This document provides a comprehensive introduction to the `epidist` package, a specialized R package for estimating epidemiological delay distributions using Bayesian methods. The package addresses k

131

Reposted by James Azam

Sam Abbott @seabbs.bsky.social · 07/05/2025

Do you like situational awareness of infectious diseases (who doesn't). Do you like thinking about modelling with this aim in mind? Do you feel like its a bit of a niche and hard to find people to talk to about it? We have a forum: community.epinowcast.org for you.

community.epinowcast.org

Epinowcast

A community to discuss epinowcast and real-time infectious disease analysis more generally

1137

Reposted by James Azam

Sam Abbott @seabbs.bsky.social · 08/04/2025

Just got asked about my review processes. I don't do that much as I am not that into the whole racket especially not whilst on a short-term contract but this is my kind of approach...

111

Reposted by James Azam

Epiverse TRACE @epiverse-trace.bsky.social · 08/04/2025

📦 R Package of the Week: {linelist} Turn data frames into #linelist objects by: ✅ Tagging key epidemiological variables (so you're not tied to column names) ✅ Validation to ensure tagged variables are of the correct type ✅ Safeguard against accidental loss of tagged variables during wrangling 1/3

132

James Azam @jamesazam.bsky.social · 08/04/2025

Interested in peer reviewing or looking to improve your skills? Peer review is an important part of the research process, but many people don’t receive much guidance on how to do it well. Fortunately, there are several helpful resources available: #research #peerreview #academicwriting #phdchat

media.tenor.com

a woman is looking at a piece of paper with a be + logo in the background

ALT: a woman is looking at a piece of paper with a be + logo in the background

120

Reposted by James Azam

Sam Abbott @seabbs.bsky.social · 07/04/2025

Flags that having the ability to specify functions as arguments in stan would be really quite amazing as not having this (or a class system) makes the code a lot more convoluted than the R equiv See here for the R: github.com/epinowcast/p...

github.com

primarycensored/R/pprimarycensored.R at f051ac82b1c6ea9bfbc280a6d7c15c91aab05b71 · epinowcast/primarycensored

Primary event censored distributions. Contribute to epinowcast/primarycensored development by creating an account on GitHub.

011

James Azam @jamesazam.bsky.social · 07/04/2025

I really enjoyed doing this (with feedback from @seabbs.bsky.social and the amazing stan forum). I'm now porting over learned wisdom to EpiNow2, epinowcast, EpiSewer, and other stan-heavy R packages. Here's a short clip showing the before and after #mcstan #stan #rpackage

121

Reposted by James Azam

UK Health Security Agency @ukhsa.bsky.social · 01/04/2025

Last week we published our first annual report on infectious disease trends. 📊 The report brings together all the key data from 2023 to early 2025 and outlines the steps our organisation is taking to tackle these threats. Read the full report 🔗🔽 www.gov.uk/government/p...

1118

James Azam @jamesazam.bsky.social · 28/03/2025

Here's a summary of our training materials.

The image is a digital graphic titled "Epiverse training resources," displaying different training materials related to the Epiverse TRACE initiative. It consists of four sections:

e-Epi training kit in Español – A Spanish-language online learning strategy for infectious disease modeling in public health. Includes a tutorial titled "Análisis de Brotes y Modelamiento en Salud Pública," marked as "pre-alpha" in development.

Research Software Curriculum – Focuses on best practices for outbreak analytics using R, including tutorials on "Version Control with Git in RStudio" (alpha stage) and "Improve your code for Epidemic Analysis with R" (pre-alpha stage).

Tutorials in English – Covers outbreak analytics topics such as "Reading and cleaning data for outbreak analytics with R," "Real-time analysis and forecasting for outbreak analytics with R," and "Scenario modeling for outbreak analytics with R," all in the pre-alpha stage.

How-to guides in English – Contains "How-to guides for Outbreak Analytics with R," also in the pre-alpha stage.

Each section includes icons for accessing the site, repository, and instructor schedules, along with development stage labels. The design has a dark gray background with white text and blue highlights.

032

Reposted by James Azam

Adam Kucharski @adamjkucharski.bsky.social · 25/02/2025

When an epidemic hits, how long does it take to get going with common epidemic analysis tasks? A couple of weeks ago, we asked representatives from over a dozen UK organisations and universities who work actively on epidemic analysis and modelling how long the below tasks would take them.... 1/

23816

Reposted by James Azam

Sam Abbott @seabbs.bsky.social · 04/03/2025

Folks, if you use substantial amounts of people's code (either as a package or just copy and paste) please cite them. Mentioning it in your SI or URL in your code repo doesn't really help as its so hard to discover and summarise for funders etc. This is quite spread wide spread for what I see.

1122

James Azam @jamesazam.bsky.social · 25/03/2025

Do check this out and let us know how we can improve it. Is there any sections you found difficult to navigate? We're iterating on this across our other packages that use stan as the backend, i.e., epinowcast, primarycensored, EpiSewer, epidist, etc. #stan

032

Reposted by James Azam

Adam Kucharski @adamjkucharski.bsky.social · 27/01/2025

One of the reasons it was possible to generate estimates so quickly was thanks to new R tools like: epiverse-trace.github.io/epichains/ primarycensored.epinowcast.org epiverse-trace.github.io/epiparameter/

2252

Reposted by James Azam

Adam Kucharski @adamjkucharski.bsky.social · 27/01/2025

Our recent pre-preprint rapid review of epidemiological parameters for H5N1 influenza in humans, and implications for potential outbreak clusters: www.medrxiv.org/content/10.1...

17428

James Azam @jamesazam.bsky.social · 19/12/2024

Converting from #markdown -> #Word, pdf, Powerpoint is easy with tools like #pandoc but the reverse conversion is not easy. Microsoft has released MarkItDown to convert documents like Word, Powerpoint, Excel, etc to markdown. Try it out. What do you think? github.com/microsoft/ma...

github.com

GitHub - microsoft/markitdown: Python tool for converting files and office documents to Markdown.

Python tool for converting files and office documents to Markdown. - microsoft/markitdown

020

Reposted by James Azam

Paul Campbell @paulc91.bsky.social · 20/11/2024

Come join the data science team at Epicentre-MSF in Paris! We're looking for someone with skills in #rstats and epidemiology to work on a vaccine trial and support MSF's outbreak response analytics. Apply below. smrtr.io/nWv_g

smrtr.io

Data Scientist (M/F), FTC 12 months, based in Paris (France)

Company Description: Epicentre is a research organization created by Médecins Sans Frontières (MSF) in 1986. Epicentre conducts field epidemiology, training and research activities for MSF interventio...

0113

Reposted by James Azam

Tana @justmostlymemes.bsky.social · 19/11/2024

forgetting your headphones at home is the modern equivalent of leaving your sword behind in medieval times

228142291481

Reposted by James Azam

Dr Roz Eggo @rozeggo.bsky.social · 15/11/2024

Starter pack of infectious disease modellers from CMMID - the Centre for Mathematical Modelling of Infectious Diseases at LSHTM. We are 150 in CMMID but just getting started on Bluesky! go.bsky.app/625gwoG

02210

James Azam @jamesazam.bsky.social · 07/11/2024

Is your presentation even that good if it doesn't have a QR code?

010

Reposted by James Azam

Bruno Rodrigues @brodriguesco.bsky.social · 22/10/2024

It is with great joy that I announce today that our (together with @PhilippBauman15@twitter.com) package rix is now on CRAN: cran.r-project.org/web/packages... Want to get started in 5 minutes? This video shows you the very basics! youtube.com/watch?v=OOu6... #Nix #RStats

youtube.com

073

Reposted by James Azam

Aki Vehtari @avehtari.bsky.social · 26/06/2024

priorsense package for prior and likelihood sensitivity analysis is now on CRAN. It works with Stan (brms, rstan or cmdstanr) fits, or just posterior draws. See more in Noa Kallioinen's post at discourse.mc-stan.org/t/priorsense... #Bayes #MCMC #rstats

discourse.mc-stan.org

Priorsense 1.0 is now on CRAN

priorsense 1.0 has been released and is now available on CRAN. priorsense is an R package for efficiently checking whether the posterior is sensitivity to changes to the prior or likelihood (see the ...

02110

Reposted by James Azam

Aki Vehtari @avehtari.bsky.social · 20/09/2024

I'm looking for a post-doc and doctoral student to join my group at Aalto to work on Bayesian workflow, cross-validation, model checking, projection predictive model selection, inference diagnostics, priors, and survival analysis (I have plenty of research ideas, pick any combination) #Bayesian

099