Quantitative Editor, @FiveThirtyEight | PhD, @LSEGovernment | 
in 
, via 
| she/her
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Everyone on even-remotely-stats-adjacent Twitter is appalled at this. I'm going to try to explain why in a thread. 1) Fitting models here is hard because the data is super noisy & changes direction every few days.https://twitter.com/WhiteHouseCEA/status/1257680258364555264 …
2) If you have really noisy data, you could estimate a model to fit it closely, but that's likely to be overfitting (e.g. here, we don't *actually* think deaths are fluctuating so much). So instead, you have to make assumptions about what the data looks like absent the noise.
But those assumptions are important to get a model that fits well out of sample. So this should be guided based on your epidemiological knowledge, your understanding of how the data was collected, and analyses of model fit.
3) Now, the "cubic fit" part: a) you're assuming a very particular functional form. And b) using polynomials to extrapolate is particularly iffy because the edge behavior of polynomials is notoriously finicky (https://en.wikipedia.org/wiki/Runge%27s_phenomenon …). This is a bad way to fit a flexible model.
4) This *could* be something more complicated like a gam with a cubic spline, but all we have to go on is the phrase "cubic fit", so... who knows? And it may well have similar issues.
5) I think a lot of the frustration here is that this hugely policy-relevant model seems like it might be based on something my third stats class told me not to do, and we don't have the information necessary to evaluate it.
Even absent the modeling problems you point out, the final answer doesn't pass the sniff test. It is making predictions that make no sense with the observed behavior of this (or any other) epidemic. /1
No other country in the world has seen their death rate drop off to near zero in a couple of weeks. Even places that went into much stricter lockdowns than anything we've done in the US took well over a month to get things under any semblance of control. /2
And the number of deaths went up again and is over 2,300 today, after a two-day drop. This has been going on for some time.
Exactly.
Every last part can be described on an exponential equation, even when the growth or extinction are very slow. Please look me up on LinkedIn. I do microbial growth equations for a living and have dealt with bacterial virus in production scale tanks (300,000 gallons)
is it reasonable to equate microbial growth in a controlled (or semi-controlled or wild) environment with infection transfer and infection spread? there will be more variables w/ disease models, right? If so, won't that effect the predicted rates?
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
