Will Hulme

The Target Trial Framework for Causal Inference From Observational Data: Why and When Is It Helpful? | Annals of Internal Medicine When randomized trials are not available to answer a causal question about the comparative effectiveness or safety of interventions, causal inferences are drawn using observational data. A helpful 2-s...

Like this, for example doi.org/10.7326/ANNA...

This is a big collaboration with University of Bristol, LHSTM, Oxford and UKHSA and you'll work with @venexia.bsky.social @jonathanasterne.bsky.social @rozeggo.bsky.social @laurietomlinson.bsky.social @ruthkeogh.bsky.social and many more great people!

As part of this hiring round we're looking for a post-doc to work with us on OVERTURE, a new NIHR-funded programme on vaccine effectiveness for flu, Covid-19, and RSV. You'll use OpenSAFELY to establish and apply optimal methods for estimating VE in population-scale data

We're hiring researchers to work on OpenSAFELY | Bennett Institute for Applied Data Science Come and work with us! We’re looking for Epidemiologists / Health Data Scientists to join our growing research team.

We are hiring researchers! We do lots of fun and important work with NHS data - epidemiology, service monitoring, developing analytic tools and methods, more.

Deadline 3 October.

Get in touch if you'd like to know more.

www.bennett.ox.ac.uk/blog/2025/09...

🚨 Funded PhD opportunity 🚨 Work with large-scale electronic health record data from #OpenSAFELY to optimise vaccine effectiveness estimation for respiratory viruses.

Apply here 👉 www.findaphd.com/phds/project...

Come see me talk about target trials in EHR data!

Hopefully this paper will shed some light (and I may have to lean on colleagues to help me understand the python code...)

Oh! Excited to read this pre-print. I have a half-drafted email where I ask you about M-Estimation for IPTW pooled logistic regression. I can get valid standard errors for the hazard at each discrete time interval, but can't get valid SEs for the cumulative incidence = 1 - cumprod(1 - haz_t).

The Causal Inference in #IDEpi Workshop provided great insight and discussion thanks to input from various speakers! @wjchulme.bsky.social of @bennettoxford.bsky.social @ox.ac.uk introduced us to challenges in estimating vaccine effectiveness in routine data #OpenSAFELY (1/3)

Great presentations on use of #OpenSAFELY from @venexia.bsky.social, @wjchulme.bsky.social, Andrea Schaffer and Ed Parker at @bennettoxford.bsky.social Symposium

ECHO – A new OpenSAFELY study on COVID-19 vaccines | Bennett Institute for Applied Data Science We’ve launched a new project to understand who received which COVID-19 booster shots, and when, and the impacts of this on health outcomes.

Blog post: We've started work on ECHO, new study of COVID-19 vaccines

www.bennett.ox.ac.uk/blog/2024/10...