Sunday, April 19, 2020

New Numbers



Last week, I had an embarrassment when a spike in total deaths on one day caused my projections of total deaths for May to spike by a factor of ten. But the next day they went back to about where they were the day before, because the day of the spike fell out of the three-day rate of change in daily deaths that I was using to project deaths going forward.

For this reason, I decided I shouldn’t be projecting daily deaths, but only the total deaths, which will be less volatile. I did a couple tests and decided I should use the three-day percent increase in total deaths (as opposed to the seven-day percent increase, which looks like it’s a little less accurate for forecasting). So all of the projections below are based on this new methodology.

I had also decided last week that there’s no point in projecting anything off of the total cases number, so I’m no longer estimating “set in stone” numbers over the course of the pandemic. Those were becoming ridiculously low; this is because reported cases are only a fraction of actual ones, and that fraction is getting smaller all the time, as far as I can see – almost certainly because of the ongoing huge shortage of testing capacity. So now I’m just showing reported cases and the daily rate of change.

I had moved last week to projecting deaths in weekly/monthly intervals, and I went all in on that today, with the table below. I decided just a couple days ago to start including May projections, and now I’ve added June. Why did I do that? Because it’s clear the epidemic in the US won’t be anywhere close to being ended in May – in fact, it will probably be going strong, if perhaps in fits and starts, through the rest of the summer. Various actions – or lack thereof – by our leaders have pretty well set that in stone.

Plus, I really don’t see any way we’ll escape having more than a million deaths over the course of the pandemic, absent a very drastic change at the top, and very soon. In other words, maybe it’s possible to keep the 3.5 million number on the last line down to close to 1 million. But it’s very hard to believe it will be anything lower than that, no matter what happens at the top.


Week ending
Deaths reported during week/month
Avg. deaths per day during week/month
Pct. Change from previous week/month
March 7
18
3

March 14
38
5
111%
March 21
244
35
542%
March 28
1,928
275
690%
Month of March
4,058
131

April 4
6,225
889
223%
April 11
12,126
1,732
95%
April 18
18,434
2,633
52%
April 25
21,188
3,027
15%
Month of April
77,528
2,584
1,910%
May 2
33,214
4,745
57%
May 9
48,463
6,923
46%
May 16
77,053
11,008
59%
May 23
120,785
17,255
57%
May 30
176,239
25,177
46%
Month of May
468,976
15,128
605%
June 6
280,213
40,030
59%
June 13
439,248
62,750
57%
June 20
640,913
91,559
46%
June 27
1,019,025
145,575
59%
Month of June
2,931,218
97,707
625%
Total March - June
3,481,779


Red = projected numbers



I. Total deaths
Total US deaths as of yesterday: 39,014
Increase in deaths since previous day: 1,867
Percent increase in deaths since previous day: 5%  
Yesterday’s 3-day rate of increase in total deaths: 20% (used to project deaths in table above)

II. Total reported cases
Total US confirmed cases: 738,923
Increase in cases since previous day: 28,651
Percent increase in cases since yesterday: 4%
Percent increase in cases since 3 days previous: 15%

III. Reported case mortality rate so far in the pandemic in the US:
Total Recoveries in US as of yesterday: 68,285
Total Deaths as of yesterday: 39,014
Deaths so far as percentage of closed cases (=deaths + recoveries): 36% (vs. 37% yesterday) Let’s be clear. This means that, of all the coronavirus cases that have been closed so far in the US, 36% of them have resulted in death. Of course, this number will come down as time goes on and more cases are closed in which the victim recovered. But this number has gone down and up since Worldometers started publishing the recovery rate on March 26 (when it was 41%), and on about half the days, it’s gone up; there is still no sign of a downward trend, and other countries like Italy and France show comparable percentages.

No comments:

Post a Comment