If you're scared about coronavirus modelling, it's worth remembering that ASSUMPTIONS ARE EVERYTHING Tiny changes make a HUGE difference
-
Show this thread
-
For example here are two models of the number of cases in Australia The only difference? Assuming a 4-day doubling rate vs a 6-day rate And yet, the divergence is vastpic.twitter.com/Cffqdb3hkr
2 replies 0 retweets 5 likesShow this thread -
Now, that's a terrible model that I quickly slapped together in Excel/Stata, but you get the idea Changing something a tiny bit on one variable can have big impacts on your end result That's why modelling is so hard
1 reply 1 retweet 5 likesShow this thread -
The really good modelers will present dozens or hundreds of options because it's all about the assumptions that you base each model on
3 replies 0 retweets 6 likesShow this thread
Health Nerd Retweeted Alexander Leverkhun
As pointed out, there's a typo in the tweet, the chart shows a doubling rate of 4 vs 5 days not 6https://twitter.com/Freep01/status/1238288961325412352?s=20 …
Health Nerd added,
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.