4 March at

Today's Numbers

From Johns Hopkins CSSE

- (click any image to enlarge it) -

JH CSSE 4 March, 2020 at 053304



World Population (to allow calculation of world prevalence of COVID-19) :


World Pop - 4 Mar - 072233


Raw and Derived Data :

CSI 4 Mar 2020 at 07h22m33s


Above, PDF



The CoronaStavelot Index (CSI) increased from yesterday, to 0.001220%. The CSI represents the best estimate of Total Confirmed Cases of COVID-19 (from Hopkins) on this date, at this time, ... divided by the best estimate of the Total World Population (Census bureau) at the same date and time.

One can express it as: "Total Confirmed Cases of COVID-19, represent 1.22 one-thousandths of 1% of the Total World Population." That's an estimate of prevalence of confirmed cases of coronavirus in the global population.


Trends 1

Trends 2 - includes active illnesses

Trends #3 : this day only, March 4, to see results more clearly, compared with Feb. 27

Trends 3 - Mar \\\' compared with Feb 27


(red bar): the confirmed cases of COVID-19, corrected for the world population on the same day, compared with those of February 27, increased by 13.36%. This is "world prevalence."

(green bar): Total Recovery after COVID-19, compared with those of February 27, increased by 35.90%.

(blue bar): the Deaths due to COVID-19, compared with those of February 27, increased by 0.70% Yesterday this figure was 0.55%.

(yellow bar): the Confirmed Cases of COVID-19, compared with those of February 27, increased by 13.38%. 

(purple bar): the number of people in the world Currently ill with COVID-19, compared with this value on February 27, diminished  by -15.49%.



  • COVID-19 Confirmed Cases continue to increase. At present, 1,832 new cases per day, up from 1,225 new cases per day on Feb 28. Warning! included in "confirmed cases" are also those who are cured. Those who died as well. This figure suggests that the virus continues to spread.
  • Those who have recovered continue to increase in number.
  • Deaths are few in number, and the death rate remains low (3.433% of confirmed cases die), increasing slightly (0.7%) when compared with that value February 27.
  • The number of people actively sick with COVID-19 worldwide (39,270 today), continues to decrease.


Rates of decline in active cases: 1st, as we have been presenting this ...

Rate of decline in active cases - Logarithmic


Here, we could pass quickly on these values, noting that the error of the estimate (the difference between today's Actual Actively Sick patients worldwide, and the Predicted value based on the nifty equation, is only 2.24%. Nice result! (And so we can move right along ...)


But, is it the best fit of the data to a trend line or curve? 

Have you been noticing that the R² value during the past couple of days, that's a measure of "fit" between the data and our logarithmic curve, has been diminishing? (I'm sure you must have noticed!).


So just maybe, something is happening to make a logarithmic relationship (changes by powers of 10), less precise. Oh ...

Is this important? Yes! And you'll see why below.

I add that in large epidemiologic, worldwide events, the numbers are so huge that talking in powers of 10 seems natural. 


How about testing a linear relationship?

Well, I've done that for us, and here it is ...

Rate of decline in active cases - Linear


Notice first the two R² values :


  • Logarithmic, R² = 0.91982 (91.9% of the change in numbers of actual Active Cases, is explained by the number value assigned to the Day of Observation).


  • Linear, R² = 0.9487 (94.9% of the change in the Active Cases, is explained by Day of Observation.


That difference may not seem huge or important. But it is.

You can see the actual equations on the charts themselves. But what these equations determine is what's important here.


  •  First, the linear trendline now has a lower error (1.35%) than the logarithmic (2.24%). That and the R² value both say that a linear relationship has now evolved to be a better fit of the actual data.
  • Second, and perhaps you already noticed. 
    • The logarithmic trend suggests that at Observation Day = 100, there will still be 35,395 Active Cases of COVID-19 worldwide.
    • The linear trend suggests that at Observation Day = 40, the number of Active Cases will be a thing of the past (-61 cases, which of course cannot be a negative value). Equally ridiculous to say it, but hear goes: On Observation Day 39.946, there will be 1 Active Case worldwide, of COVID-19.
    • Since Observation Day 0 was on February 27, 2020, the COVID-19 problem worldwide will end on April 6, 2020.


Have a look ...

Rate of decline in active cases - Logarithmic (v2)

Logarithmic just doesn't fit anymore ...


Forecasting has its dangers. But, you read it here first. April 6th, it's over.

This good news may be harder to accept, if locally you are facing, as we are here in Belgium, the tsunami as it begins to pass your island.


<<<<<<<<<  Home


0 Poster un commentaire

Inscrivez-vous au blog

Soyez prévenu par email des prochaines mises à jour

Rejoignez les 13 autres membres