Monday, June 8, 2020
COVID-19 June 07, 2020
Once again, nothing new to report. The trends are trending as they have. A handful of states continue to show some breakout statistics. I expect more of that, and if enough hop on that train we will start to see it reflected in the national tally.
Sunday, June 7, 2020
COVID-19 June 06, 2020
I've been showing the Gompertz curve along with both the infection data and the death data. The Gompertz model failed long ago for the infections, which have plateaued for weeks rather than decreasing as the model predicted. In the last couple of weeks, the death statistics have also departed from the Gompertz model. Neither of these is surprising.
Today, I attempted to fit new curves to the data, ignoring earlier data, and focusing instead on trying to better match more current data. That exercise failed completely for the infection data. There is no Gompertz curve (or similar so-called logistic/S curves that will fit the data). The death data is a different story, however. If you focus only on the data from about mid- to late-April and ignore prior data, there is a curve that shows a reasonably good fit. It's a terrible fit with the earlier data. You can see that misfit when I plot the curve and data on the old semi-log plots. The curve and the data are very far apart right up to April.
The new curve suggests a total death tally of 120,000. Note that this number is the number based on the data set that I'm using, which tends to be lower than others by 10-20%. So, if you prefer other data sets, my 120,000 would probably translate to something like 130,000-150,000. As always, this assumes the data continues to follow the curve. There is no reason to suspect that it will. What the new Gompertz curve does do is give a more current baseline that can be used to provide context for the data. Are we staying on the curve? Rising above? Falling below?
Also, I've updated stats for Texas, which I'm showing below. Texas is one of the states that seemed to be showing a noticeable increase in infections. The analysis seems to bear that out. There are others that seem to be showing similar trends. I don't have time to analyze all those data. There are other websites that allow you to see stats by state if you are inclined to dig further.
Today, I attempted to fit new curves to the data, ignoring earlier data, and focusing instead on trying to better match more current data. That exercise failed completely for the infection data. There is no Gompertz curve (or similar so-called logistic/S curves that will fit the data). The death data is a different story, however. If you focus only on the data from about mid- to late-April and ignore prior data, there is a curve that shows a reasonably good fit. It's a terrible fit with the earlier data. You can see that misfit when I plot the curve and data on the old semi-log plots. The curve and the data are very far apart right up to April.
The new curve suggests a total death tally of 120,000. Note that this number is the number based on the data set that I'm using, which tends to be lower than others by 10-20%. So, if you prefer other data sets, my 120,000 would probably translate to something like 130,000-150,000. As always, this assumes the data continues to follow the curve. There is no reason to suspect that it will. What the new Gompertz curve does do is give a more current baseline that can be used to provide context for the data. Are we staying on the curve? Rising above? Falling below?
Also, I've updated stats for Texas, which I'm showing below. Texas is one of the states that seemed to be showing a noticeable increase in infections. The analysis seems to bear that out. There are others that seem to be showing similar trends. I don't have time to analyze all those data. There are other websites that allow you to see stats by state if you are inclined to dig further.
Saturday, June 6, 2020
COVID-19 June 05, 2020
Another fairly short post today. Trends continue to do their thing without much surprise. I am watching a few states out of the corner of my eye: Texas, North Carolina, Florida. These states look to breaking out ahead of the pack. I'm also watching Puerto Rico, which is showing some possibly troubling numbers. PR is particularly concerning because our fellow citizens have been hit so hard from natural disasters and the federal government doesn't care much for its brown, Spanish speaking citizens.
Friday, June 5, 2020
Thursday, June 4, 2020
COVID-19 June 04, 2020
No real changes from yesterday. Stay safe and don't let your guard down. Although we no longer have the explosive growth we saw in early March, the number of new cases is not decreasing. More importantly, there are currently more people infected that at any time in the past. Going strictly by numbers, each day that goes by your chance of infection increases, at least if you're out there mixing it up with society. On the other hand, mask use and general awareness may make a big enough dent in transmission probability that the risk of infection could be lower than in the past even though the overall number of cases is still growing. In any case, this is no time for complacency.
Wednesday, June 3, 2020
COVID-19 June 03, 2020
Yesterday's death toll came in higher than the Gompertz model (again) and is clearly indicating a change in the slow decrease that we've seen for a month or more. It's now flat if not slightly increasing. The next few days should be when the highest numbers for the week roll in. Unless they are much lower than expected, it's hard to see how this new trend is going to reverse.
Meanwhile, the daily new infections are still bouncing at or just above 20,000 per day. There is a slight indication of an increase in the rate in 7-day average, but not enough to call it a reversal of the trend. For context, we are currently at daily rates that are comparable to what they were at the end of March. On the other hand, the peak 7-day average was just a bit over 30,000 in early April. So, while things have improved compared to the peak, the numbers are still high, and this is after the fairly austere policies that have been in place for months.
Meanwhile, the daily new infections are still bouncing at or just above 20,000 per day. There is a slight indication of an increase in the rate in 7-day average, but not enough to call it a reversal of the trend. For context, we are currently at daily rates that are comparable to what they were at the end of March. On the other hand, the peak 7-day average was just a bit over 30,000 in early April. So, while things have improved compared to the peak, the numbers are still high, and this is after the fairly austere policies that have been in place for months.
Tuesday, June 2, 2020
COVID-19 June 02, 2020
I've been waiting for/wondering when the death rate would start to flatten in concert with the number of new cases. New cases have been nearly flat with only a very slow decrease for weeks. I'm not quite ready to make the call, but the 7-day average of death rates appears to have departed from the Gompertz model curve. As I've said repeatedly, you can't really look at daily numbers and even the 7-day average can be squirrely. It could very well turn around in the next day or two, but if not...well, the long-awaited response in death rates has arrived. Will the orange 7-day average in the daily plot continue to diverge from the red Gompertz curve?
Subscribe to:
Posts (Atom)