This is what you were wondering @jack_milroyhttps://twitter.com/PWGTennant/status/1258506049067216897 …
It's complex. Basically, this model isn't constructed to measure smoking->death due to COVID-19. By controlling for a number of potentially inappropriate things in the Cox regression, they may have changed the impact of smoking on risk of death
-
-
For example, smoking causes diabetes, and diabetes causes an increased risk of death from COVID-19. By controlling for both of these in the same model, we are seeing the impact of smoking sans the negative effects of smoking in diabetes. Same with respiratory and heart disease
-
Ah the old "controlling for a cause" problem! Thank you.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.