Friday, November 20, 2020

Friday's Are the Bomb

It's Friday, and today's initial number of total cases for the state (170,584) shows the second highest daily increase at 4,588.

The record? Last Friday with 5,352. 

That's good, right? You know, that we didn't set a new record? 

Gosh I hope so.

But, there's also stuff to darken your mood. 

As has been typical, we set another record for cases over the last 7 days (24,795). I remarked the other day that this is something we probably will have with us until the pandemic/wave really, really, eases up.

More disturbingly, the growth rate in total cases over the last 7 days is up to 17%. That is the highest since mid-July, when Utah was on the edge of the huge run-up in Arizona. 

Further, this percent has been inching up this fall (again, something I've talked about before). It was down around 5% around Labor Day. Then it rose rapidly to 10% before stabilizing. That held until Halloween. But it's been inching up consistently ever since.

Keep in mind that a percentage change is a statistic that is often quite stable even when the levels data is "growing exponentially". So the right phrase for what is going on in Utah should be something like "growing faster than exponentially". There isn't a great word for that, but sometimes people use hyperbolically: so visualize how a time series would rise more quickly as it approached an asymptote (there's no asymptote for this data, but the visualization still works).

****************************************

On a different note, I haven't been keeping tight track of the data, but the tweets from the Southwest Utah Rural Health Department indicate that active cases in Iron County have tripled since Halloween. 

Snark: well, at least we can be glad that while the outbreak has gotten worse as it's gotten colder, at least it won't be getting any colder than this. Geez.

Wednesday, November 18, 2020

More Records for 7 Day Totals

Utah seems to have gotten over its data glitches.

But, we again set records today and yesterday for cases over the last 7 days.

On the bright side, it's possible there's slowing in those numbers. For the last 6 days, the total for the preceding week has been less than 30% higher than the previous week. But if we go back to the 6th through the 10th, those weekly totals came it at as much as 48% higher than the previous week.

Those work out to multipliers like this. Today's total for the last 7 days (22,308) is 1.23 times the total for the preceding 7 days from a week ago (18,107). But we're going to keep setting records until that multiplier gets a lot closer to one.

Monday, November 16, 2020

Did Utah's Wave Just Crest?

Did we just crest, or is this another data glitch?

Positive cases were not high today, but it's Monday. They're always low on Monday's (reflecting that the data reported Monday is from tests done on Sunday). 

But importantly, it's lower than last Monday, and by quite a lot (2209 to 1971 in the preliminary data).

Also, we did not set a new 7 day high for cases today (we fell short on that by a bit, 20,742 vs. 20,980).

This bears watching. Viruses don't have waves. People do. Perhaps the Governor's state of emergency got peoples' attentions.

Sunday, November 15, 2020

Gonna' Need a Dummy Variable

Not really sure what the story is, but there's been a data glitch in the reporting of cases for Utah.

The data reported on Friday the 13th (go figure), for Thursday, November 12th, show far fewer cases than are reasonable to expect.

A data glitch produced artificially low coronavirus case numbers on Friday in Utah, with “only” 2,150 new diagnoses reported, state health officials said.

... 

For the past week, the state has averaged 2,616 new positive test results a day, but that figure also reflects the data glitch producing artificially low numbers of new cases; the true number is higher than that, UDOH reported. For the past week, 23.5% of all tests have come back positive — also potentially affected by the reporting error.

The glitch caused the string of 25 straight days setting a new record for cases over the last 7 days to an end.

Not surprisingly, the "catch up" data released on Saturday the 14th showed a new record in cases over the last 7 days. That's a total of 55 records since September 1st. 

Go Utah!

Sunday, November 1, 2020

Revisiting Forecasts and Making New Ones

Here's what I forecast about 10 days ago, taking us through October 29th (oops ... what I wrote below as Saturday was actually Friday, and the rest of the labels are one day late too):

  • Saturday: total cases at 102,627; new cases at 1,118
  • Sunday: total cases at 103,833; new cases at 1,207
  • Monday: total cases at 105,118; new cases at 1,285
  • Tuesday: total cases at 106,307; new cases at 1,189
  • Wednesday: total cases at 107,807; new cases at 1,499
  • Thursday: total cases at 109,504; new cases at 1,697
  • Friday: total cases at 111,660; new cases at 2,156

Here's what we got. Do note that my forecasts were based on the updated numbers from Wikipedia, so I compare to those updates too (the Utah Dashboard does not update old numbers).

  • Friday: actual total cases 103,192, I was too low by 565
  • Saturday: actual total cases 104,992, I was too low by 1,159
  • Sunday: actual total cases 106,171, I was too low by 1,053 (whoo-hoo, a little improvement)
  • Monday: actual total cases 107,289, I was too low by 982
  • Tuesday: actual total cases 108,863, I was too low by 1,056
  • Wednesday: actual total cases 110,687, I was too low by 1,183
  • Thursday: actual total cases 113026, I was too low by 1,366

Can you say biased? Let's fix that.

In my simple model, I assumed a 10% growth over 7 days previously. If I'd assumed 11% my forecasts would have been (at least to my eye) unbiased. What I could not have known 10 days ago was that the rate of growth would crank up from 10% to 11%. 

It's been hanging a tad on the high side of 11% this for about a week, so this time I'll assume 11.1% growth. And I'll be more careful about my labels. I'm writing this about 11:55 on Sunday night. The number I'm forecast first is the announcement that will be made on Monday afternoon for the total cases reported through the end of today. So, on the Utah dashboard it will be announced on 11/2, but on Wikipedia it will be labeled for 11/1. Here goes:

  • Monday: total cases at 117,956, for an increase of 1,446
  • Tuesday, total cases at 119,198, for an increase of 1,242
  • Wednesday, total cases at 120,947, for an increase of 1,749
  • Thursday, total cases at 122,973, for an increase of 2,026
  • Friday, total cases at 125,572, for an increase of 2,599
  • Saturday, total cases at 127,425, for an increase of 1,853
  • Sunday, total cases at 129,442, for an increase of 2,017

Of course the problem with this is that I'm forecasting levels by assuming growth rates will remain constant. And last week they didn't. This week they might, or they could go down, or up. 

Oh, and those pesky records for 7 day totals: we've set a new record each of the last 14 days.