A mathematical model and forecast for the coronavirus disease COVID-19 in Ukraine (M1)
(A.B. Alyokhin, B.V. Burkynskyi, A.N. Grabovoi, V.A, Dilenko, N.I. Khumarova)
04/10/2020. No F-218.
Today, the base 7-day forecast period of the COVID-19 epidemic development in Ukraine, compiled using the M1 model according to statistical data, has expired. The forecast made for the period from September 28 to October 7 inclusive data of September 27 and published by us on September 27, 2020 (see https://www.facebook.com/ab.alyokhin/posts/184338443209059).
Despite the dramatic development of the epidemiological situation in Ukraine over the past weeks, the accuracy of our forecasts remains at a high level. This, in our opinion, is more due to the coronavirus and its programmed behavior than the person who promised the accuracy of the forecasts, put much less effort to change the situation than the coronavirus, which, unlike it, works day and night, “tirelessly” …
The results of evaluating the accuracy of the current forecast are presenting in table. 1–2 and fig. 1–11.
Table 1 shows the calculated and actual values of the main indicators of the COVID-19 epidemic in Ukraine for a 7-day forecast period. The absolute and relative errors of daily forecasts, as well as the average absolute error MAE and the average absolute error in percent MAPE, including the same MAPE * estimate on an accrual basis, the forecast as a whole.
Table 2 shows the same data for case fatality rates I (TC), I (CC) and the IP progress indicator.
Average absolute percentage errors (MAPE estimates *) for the main indicators of the COVID-19 epidemic in Ukraine are at the following level:
- total number of infected people — 0.44%;
- total number of deaths — 0.67%;
- total number of recovered — 0.53%;
- number of active cases — 0.45%.
The errors in forecasting the most important derived indicators of the COVID-19 epidemic in Ukraine (MAPE * estimates) are as showing in Table. 2:
- mortality rate I (TC) — 0.61%;
- mortality rate I (CC) — 0.54%;
- IP progress indicator — 0.21%,
Visually, the degree of correspondence between statistical and forecast data is showing in Fig. 1–11.
In Fig. 1–4 indicate:
- actual trajectories of the main indicators of the COVID-19 epidemic in Ukraine;
- calculated trajectories of these indicators for the same period, as well as for a lead period of 10 days;
- boundaries of confidence intervals (ranges of possible deviations of a point forecast with a significance level of p = 0.01).
In Fig. 1, the boundaries of the confidence interval hidden due to their imposition on the main graphs.
The diagrams in Fig. 5–8 reflected:
- actual trajectories of changes in the daily indicators of the COVID-19 epidemic in Ukraine over the entire observation period;
- calculated trajectories of these indicators for the entire observation period, as well as for a 10-day forecast period;
- boundaries of the confidence intervals of the 10-day forecast (p = 0.3).
Diagrams Fig. 9–11 reflect:
- actual trajectories of lethality indicators I (TC) and I (CC), as well as the IP progress indicator for the entire observation period;
- calculated trajectories of these indicators for the entire observation period, as well as for a forecasting period of 30 days.
All these diagrams clearly demonstrate the high accuracy of forecasts, which means, in addition to the high quality of our work, the preservation of the negative trends in the development of the epidemiological situation in the country formed in the pre-forecast period and the absence of effective efforts to curb the spread of coronavirus by society.
Sources of statistical data:
Our materials also:
Accuracy of our forecasts:
Publications on case fatality rates and progress indicator