> Using a large database of (deidentified) medical records, the researchers compared the outcomes of people taking a GLP-1 for their type 2 diabetes to people taking other common diabetes drugs between 2017 and 2025. GLP-1 users were significantly less likely to be diagnosed with TB for up to a five-year span, they found.
This is incredibly manipulative. So, we're going to ignore all other factors that may have played into this and just assume it was due directly to GLP-1 use?
Yes, p-hacking happens, incentives in academia are increasingly misaligned etc, but I assume that there are competent people and systems to avoid such obvious issues? It's science 101 to avoid spurious correlations. Sure there might be some tricky ones, but if the's obvious one that came to your mind, very good chance it's been accounted for.
You read reporting about a study, made assumptions that it was bad, and posted your opinion without actually reading the study to see whether the scientists involved were smart enough to try to rule out other factors.
I read a news report on the study that was linked, yes. But my issue isn't with the researchers/their process, it's with how this is presented in the headline vs. what the actual reason was backing the claim.
There's nothing to "do better" about; you just don't like my opinion (and that's perfectly fine).
This is incredibly manipulative. So, we're going to ignore all other factors that may have played into this and just assume it was due directly to GLP-1 use?