Oh, bloody hell, Nate. If anything, the process as designed is a bit too lax when it comes to approving drugs.https://twitter.com/NateSilver538/status/1357704397824876544 …
-
-
Oh, definitely. Ditto scientists in the physical sciences, like physics, chemistry, etc. They don't understand the complexities and biases baked into epidemiological and clinical trial data and think that analyzing such data requires just a good knowledge of statistics.
-
Exactly. I think those areas also attract a lot of people who like how absolute and non-fuzzy their chosen discipline is so that makes all the uncertainty of a public health crisis tempting to reduce to "controllable" statistics.
End of conversation
New conversation -
-
-
I know quite a few people who work in AI and data, good people but they often fail to understand that data is often flawed and medicine is much more than just data.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I would disagree. Data scientists and statisticians are a heterogeneous bunch, and generalisation based on anecdotal instances is bad. Clinicians and biologists can be equally rubbish at designing and interpreting high-throughput experiments and large data sets.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
Show additional replies, including those that may contain offensive content
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.