I don’t think data availability is the only issue here. There are several decisions made before the data collection that can impact the results of a trial

Problem with defining a heterogeneous patient population with an intervention they are receiving. I commend the authors of the RCT. I don’t think they would want the conclusion to be widespread use of fish oil quite yet. I think we can do better in nephrology research!

Looks like selection bias, index date bias…

As someone who spends a lot of time thinking about noise, measurement errors and analysis of autonomic measurements (not just “HRV”) this is making my head explode. Sooo bad

Your casual autocorrects to causal. Not surprised 😁

It’s my favorite quote!

How about instead:

I never get to see the future with all the good studies I have been promised in all these papers sigh!

It’s gotten more attention due to the meta-research showing women scientists tend to self-cite less than men

If someone lacks such basic level of curiosity maybe they shouldn’t be doing research

"Uncooperative statistician": the term used (typically by a senior clinician) to describe a well-trained and knowledgeable statistician who refuses to conduct flawed or fraudulent research.

What worries me? Statements like "searching for biological causes is bound to be unproductive" and studying exposures "diverts funding from more important issues."
That's a false dichotomy! We can tackle overdiagnosis AND investigate why more young people are getting cancer. 10/