Could there be a target trial that identifies the natural (in)direct effect? Yes, but it requires assumption that essentially mean we can turn back time.
Things that do not require mediation analysis:
- effects of one treatment on multiple outcomes (causal exploration)
- decide whether to intervene on the treatment on the mediator (comparing two total effects)
- combined interventions on treatment and mediator (e.g., what if the mediator was fixed)
arXiv📈🤖
AI-Assisted Variance Reduction in Randomized Experiments
By Arbour, Ben-Michael, Feller et al
ArXiv Paperboy (Stat.ME+Econ.EM)
Julia M. Rohrer
Julia M. Rohrer
#ICA2026 was truly a blast in the beautiful city of Cape Town!! What better way to end the conference by announcing our June Scholar-in-the-Spotlight: @lisemarienassen.bsky.social! She is a postdoc at the University of Amsterdam. Read our interview with her here: www.icamobile.org/scholar-in-t...
Gino seems a clear case of a fraudster having been exposed with undeniable evidence.
The effort required to produce that evidence for one person is staggering—likely six or seven figures in time, legal costs & expert labor.
What does that imply about academia’s capacity to expose fraud at scale?
I like this @thejop.bsky.social :
"We are now implementing a system in which the editorial team has the right to not consider submissions from authors who have failed to review for the journal three or more times, when invited to do so by the editorial team."
#Pride2026 #DiversityInResearch
At GESIS - Leibniz Institute for the Social Sciences, we are committed to democracy and an open society. These values are reflected not only in our research, but also in our workplace culture. Let us continue to promote equality and celebrate diverse identites!
Now that's what I call a spicy opeing: Understanding mechanisms is not a research question.
ICA Mobile Communication
Julia M. Rohrer
Alexander Wuttke
Morten Paul
GESIS - Leibniz-Institut für Sozialwissenschaften
Danbischof
Gute Frage, @mortenpaul.bsky.social – ich hoffe auf erhellende Antworten, @verbrecherverlag.bsky.social
Ingo Stützle
Why we should rethink causal mediation, and what to do instead? Come to hear the answer from Vanessa Didelez at the next CIIG seminar!
The seminar will be hybrid. If you are in London, come join us in person at UCL! Otherwise, you can join on Zoom as usual. Registration links in comment below.
Georgia Tomova
The forensic report is available here: storage.courtlistener.com/recap/gov.us...
Incredible stuff
Malte Elson
The testimony of Julian Ackert, the forensic expert in the Gino case, is fascinating for computer nerds. <raises hand>
Whoever changed the metadata might have gotten away with (at least part of) it if they had remembered to include seconds in the timestamp.
