Thiago

I use 42 as seed. I m always trying to answer the ultimate question! Haha.
Ehr, about llm. Even within staff I m seeing this. Now everyone is a R expert, creating (llm) code for very complicated models out of thin air

Hmm. I think the umbrella of the black box also catches the FAW. There's a commentary from Greenland and colleagues that defines black box epi as an atheoretical search for associations (10.1097/01.ede.0000134867.12896.23)

Hmm. I would consider those tables as "factors associated", as there are some stratifications/etc. Also, in 1944 probably wasn't straightforward to do regression. I'm not totally against these types of studies, especially in fields with no substantial prior information

This discussion (factors associated) is very old. But the name before was "black box Epidemiology". Weiss (10.1097/01.ede.0000135175.11460.27) comment about how sudden infant death vs prone position sleep was first seen in black box epi.

The worst part is that a lot of people think the same, but without owning an AI/ knowing how biased Grok is towards Musk's opinions (my assumption of AI/person). The grok even checked Musk's Twitter to reply to "sensible topics"

Is academic research becoming too competitive? Nature examines the data Applications for European research grants increased in 2025. Scientists say they’re feeling the competition.

www.nature.com/articles/d41...
This ultra-competitive scenario makes me very anxious.
1) almost a lottery
2) It is possible that the lottery would be more fair, as at least it wouldn't have the conscious/unconscious bias (mainly the "weights" the institution of origin carries)

In the Apple world, "you are using them wrong"
(I have no idea, no iPhone /airpods)

a man is playing a video game with a screen that says i-beat ALT: a man is playing a video game with a screen that says i-beat

It will be only a bigger loot box (compared to the UK biobank).
A Methodologist looking at someone publishing baked "association" studies.
🤣

To be fair. Only gregg semenza has a considerable amount (15) and I think it's the most problematic case

Retractions by Nobel Prize winners In 2017, our co-founders wrote an intentionally ridiculous column in Slate: “Want to Win a Nobel Prize? Retract a Paper.” But Nobel Prize winners have indeed retracted papers — so…

You don't need to. The retractionwatch already did
retractionwatch.com/retractions-...

We are regulated, but without any punishment for breaking the rules. Just see nobel laureates with vast collection of retracted papers and keeping their jobs

Evaluating the cost-effectiveness of COVID-19 mRNA primary-series vaccination in Qatar: An integrated epidemiological and economic analysis Qatar implemented a mass primary-series vaccination campaign to mitigate the impact of the coronavirus disease 2019 (COVID-19) pandemic. This study aimed to retrospectively evaluate the cost-effective...

@grahamkendall.bsky.social you could check the pattern of self citations of this group : journals.plos.org/plosone/arti...
Every paper of them in this topic cite almost all of the previous ones. Rarely citing other groups

Luxury = be exploited for the profits of the publishers.
But AI is not the solution; more likely, we need a different system.
The current way is doomed (just look at the waves of paper mills in "peer reviewed" journals)

Kinda funny the list of authors. First and last from uni, all others google. Looks like an attempt of get some "validation" from academia

It sounds fancy. Who needs research when you can fund thin air?

Perinatal outcomes of symptomatic chikungunya, dengue and Zika infection during pregnancy in Brazil: a registry-based cohort study - Nature Communications In this study of ~7 million Brazilian births, the authors show that chikungunya, dengue, or Zika infection during pregnancy is associated with an increased risk of adverse perinatal outcomes, with the magnitude of these effects varying by trimester of exposure.

A study of ~7 million Brazilian births shows that infection with #chikungunya, #dengue or #Zika viruses during pregnancy is associated with increased risk of adverse perinatal outcomes

@csthiago.bsky.social

#viruses #epidemiology #pregnancy

P.S. (Anecdotal evidence) When my affiliation changed from "Fundação Oswaldo Cruz" to "London School of Hygiene and Tropical Medicine", I started getting way more peer review invites....

In the field of epi, I got some rejections due to a clear misunderstanding by the reviewers. As even in my papers about Brazil, the vast majority of the reviewers are from the global North, with no expertise whatsoever about Latin America.

The BBC article about the paper. God... "hormone reboot"... From a survey paper....

It looks that there is a problem with the statistics as well. The propensity score only uses baseline variables and treats them as time fixed. But, a second infection is a time-varying exposure. So, the "unexposed" group has been defined conditionally on the future. Right, @pwgtennant.bsky.social ?

Also mediation with counts

Help!
Where can I find resources about causal mediation of ordinal outcomes? (using SEM)

Thanks 😄
#rstats @dingdingpeng.the100.ci

Updates about it. The CIs are likelihood ratios CIs, which can be very asymmetrical.
About the cumulative incidence, they have reinforced me that the all lower exposure curves initiate before the higher doses one.
(I still feel a bit uneasy with almost all low CIs being 1)

I’ve had the same impression while looking at academic epidemiology postdoc offers. So much focus on AI, machine learning, LLM experience. Are these the core skills we need now? What about subject matter knowledge, study design, bias, statistics, population health knowledge? Outdated?

I haven't contact them / or post on pubpeer. Someone shared this paper with me today and I found it those bits very strange.
I will email them tomorrow

Oh. I haven't paid close attention to this figure. There are even participants starting not at 0%.
About the "rr" is complicated to know, once they have used time varying exposure and idk how to interpret cum incidence in this context.

About the RR (relative risk in the paper, not risk ratio), which is the HR is... but to me looks misleading

Sleuths,
Can someone explain to me how these CIs are possible?
www.nejm.org/doi/full/10....
It is not clear how they got RR from the Cox PH, as it would require choosing a time point (looks like an interpretation of HR as RR)

@lonnibesancon.bsky.social @sophieehill.bsky.social @retractionwatch.com

Thanks! I will take a look

2/2
The outcome model has multiple categorical variables; I only found binary and continuous methods in MICE (for mixed models). Any ideas?
#rstats #episky