Noah Greifer Agree that people should be using DAGs to select adjustment variables, but I would go a step further & say that it’s not about what the properties of a confounder are or aren’t. Instead we should focus on confounding and stop treating confounders as a variable type

Dr Ellie Murray, ScD Anders Huitfeldt I guess I think it's useful to differentiate between variables that cause confounding bias due to causing both the exposure and outcome, and variables that we can use to reduce confounding bias (eg the 'surrogate confounder' as (inaccurately?) shown in the DAG review). 🤔

This study reviews recent research on the link between gut microbiota and the brain, and the microbiome’s role in shaping the development of the most common neurological and psychiatric illnesses. Read the study in Frontiers - Medicine ⬇️

Our review is out 😃

Excited to have witnessed the first national conference on infectious disease modelling! 🤗 congrats to Lilian Kojan from Universität Lübeck & Libbie from Domenech de Cellès lab for winning the best posters! #MONID #BMBF

Blood-brain barrier is difficult to penetrate and therefore can protect us. This study suggests bacteria can hijack the pain signalling pathway to suppress the host defence in order to invade the brain: nature.com/articles/s4158… Other ways of pathogens crossing BBB👇🏽

We published a new article in Am J Epidemiology 🎉 and proposed a new approach – using #LassoRegression to predict the #counterfactual – to infer the impact of # pneumococcal conjugate vaccines. LINK: ow.ly/IVHI50Nn7oK A thread (1/7)👇

Our paper is out 🤗 Jess Rohmann is on BlueSky and LinkedIn Tobias Kurth Ulrike Grittner Domenech de Cellès lab thank you again for working with me on this project!

We are thrilled to announce the next YSLS to announce Julian Rodemann talk on April 18 at 4pm. ➡️Registration: rebrand.ly/ysls-regist Feel free to register and apply for your own talk. #Statistics #stats #biometrics #YoungScientist

could be that some of the treatments for shingles pain is causing the alzheimer’s, ev gabapentin

One of my favorite papers in recent years included this diagram. It shows the impact of controlling for three different types of variables: confounders, colliders, and mediators. With confounders, control is good. With the others, you ruin your result by controlling.

Now I know other than lubridate, there is also hms for plotting time series in R – jotting this down for future use ^__^

Did you miss any of the #IDEpi2023 seminars? Recorded seminars, when made available by the presenter, can be found on our YouTube channel! bit.ly/3oK8Bfw

Over 100 governments in low- and middle-income countries have introduced anti-poverty cash transfer programs over the last 3 decades In new research, we examined the effects of these initiatives on the ultimate health outcome — mortality Published today in nature /1

This Wednesday 4pm (CEST) Berlin Epi Methods – I am presenting a method to estimate #vaccine impact and some findings from our recently published study: doi.org/10.1093/aje/kw… Looking forward to seeing you in person or online!

🔜 Bereit für die Lange Nacht der Wissenschaften? Morgen geht's los! Verpasst nicht unser Highlight des Abends - den Science Slam der Institute zwischen Max Planck Institute for Infection Biology, DRFZ und #MPUSP 🤩 Seid dabei um 20:30 Uhr auf dem Campus Charité Mitte!

"Everything is related to everything else, but near things are more related than far things" (Tobler 1970) 🌎 Very excited to be at UW Biostatistics #SISMID2023 in person this year 🤓 gonna learn some spatial analysis today! 🗺️

This is how I advise my #PhD students to write research manuscripts (in case someone finds it helpful). General points: 1. Research questions addressed by your manuscript are key and should guide you. 2. Don’t view your manuscript as an article. See it as a STORY. 3. Pick the

Yes I will offer my online science-focused Statistical Rethinking course again starting in January 2024. Registration going up at the end of this month. All the course materials are already online though, so why wait? Update your posterior today youtube.com/watch?v=FdnMWd…

"The statistical properties of RCTs and a proposal for shrinkage" from van Zwet, Schwab, and Senn > "we believe it is important to shrink the unbiased estimator, and we propose a method for doing so" Open Access: doi.org/10.1002/sim.91…