April 1:
Colorado looks to be over the hump. To do a better projection, I’d only have to adjust the death rate.
Let me show that… (slide 2)
And to track it really, really, tight… I will change formats… (slide 3)
That new smaller peak on the bottom is the “slope” of the big grey “S” shaped curve (called a “sigmoid”). It tends to be noisy, but is a good indicator of whether we are speeding up or slowing down.
Right now, Colorado is slowing down! They must be well-behaved. When all this is over, it will be interesting to look for correlations.
March 30:
Just added data.
March 29:
Just added data. New format.
Peak?
March 26:
Took the opportunity to adjust a smidge. Sorry, they had 8 deaths there today.
March 25:
Just added data. Looks like testing anomaly.
March 24:
Once we have data for halfway up the peak, we can usually make a very close prediction. It’s been challenging in lots of states however, because the deaths numbers are so low (noisy) and right in the middle of the most important part for predictions, they changed the testing protocols, messing up the cases data. Maybe the right public health policy, but certainly bad for the scientific method.