My new piece is about lockdowns, shoddy science, and why it's so hard to know which specific COVID-19 intervention is the most effective at controlling spreadhttps://gidmk.medium.com/do-lockdowns-work-879e93803d67 …
-
-
Replying to @GidMK
What's your definition of 'modelling research'? I would have thought it's about having some epidemiological model for the course/wave of the pandemic in which a new restriction then affects some parameter that then affects outcomes. That's not what Ioannidis et al. do though.
1 reply 0 retweets 1 like -
Replying to @AndreasShrugged
I think any study that primarily uses modelling to answer a question could be defined as modelling research
1 reply 0 retweets 0 likes -
Replying to @GidMK
Hm...my economist's distinction might be that a theory-based prediction/simulation model could not inform us about causality between a policy and an outcome. A reduced-form regression model could, under a set of assumptions. Clearly, these assumptions don't hold for Ioannidis.
1 reply 0 retweets 2 likes
Yes that's a fair point. I think I used the term modelling in the article more as a colloquial piece of language than a technical distinction. Makes more sense than "retrospective epidemiological study" imo
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.