Third expert from the top really hedging their bets.
Overconfidence is a pernicious bias, even in experts. It's astounding how few experts' confidence intervals included the correct estimate of #COVID19 infections in the US by 3/29 when forecasting for just two weeks in the future. (of course, non-expert estimates are even worse)pic.twitter.com/pa6oMDp2wV
-
-
-
Wisely, I'd say!
- 6 more replies
New conversation -
-
-
Pretty shocking, given simple maths. About 1700 cases on the 14th. Doubling every 2-3 days. So between 1700*2^5 and 1700*2^7. Admittedly a wide range, but that’s the nature of exponentials with uncertainty on the doubling rate.
-
It was a function of the number of tests the US was doing at the time and the perceived ability (or lack-thereof) to ramp up. If you’re doing 10K tests a day, pretty impossible to get to 150K cases in 2 weeks unless literally everyone tests positive
- 5 more replies
New conversation -
-
-
It’s not just overconfidence, it’s also a failure to understands exponential growth. Another way to put that is they asked the wrong type of expert. I encountered deeply skeptical responses when did this forecast (shown to be correct) for the UK.https://twitter.com/actuarybyday/status/1241443148125085697?s=21 …
-
They surveyed only functionally innumerate "experts" (presumably the same empty suits in think tanks and schools of public health who opposed every action to suppress outbreak, including border restrictions, cordons sanitaires, lockdowns, quarantines, school closings and masks.)
End of conversation
New conversation -
-
-
Good example for elucidating both varieties of overconfidence: (1) Overoptimism: On average beliefs were that we'd have far fewer cases than we do (though this could have been pessimism about testing). (2) Overprecision: Prediction intervals seem excessively narrow.
-
So much #2. It's an exponential function. That's going to be crazy hair triggered. Should be estimating within orders of magnitude.
End of conversation
New conversation -
-
-
Hey
@katy_milkman you seemed to have missed our follow up (and we'll do another this week) that shows a different picture in case estimates from the surveyed experts. It takes time to understand what's happening. https://fivethirtyeight.com/features/experts-say-the-coronavirus-outlook-has-worsened-but-the-trajectory-is-still-unclear/ …pic.twitter.com/UDWIS0mLJ1
- 1 more reply
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.