Background:
COVID-19 cases have been reported as a global threat and several studies are being conducted using various modelling techniques to evaluate patterns of disease dispersion in the upcoming weeks. Here we propose a simple statistical model that could be used to predict the epidemiological extent of community spread of COVID-19from the
explicit data based on optimal ARIMA model estimators.
Methods:
Raw data was retrieved on confirmed cases of COVID-19 from Johns Hopkins University
(https://github.com/CSSEGISandData/COVID-19) and Auto-Regressive Integrated Moving Average (ARIMA) model was
fitted based on cumulative daily figures of confirmed cases aggregated globally for ten major countries to predict their incidence trend. Statistical analysis was completed by using R 3.5.3 software.
Results:
The optimal ARIMA model having the lowest Akaike information criterion (AIC) value for US (0,2,0); Spain
(1,2,0); France (0,2,1); Germany (3,2,2); Iran (1,2,1); China (0,2,1); Russia (3,2,1); India (2,2,2); Australia (1,2,0) and South
Africa (0,2,2) imparted the nowcasting of trends for the upcoming weeks. These parameters are (p, d, q) where p refers to
number of autoregressive terms, d refers to number of times the series has to be differenced before it becomes stationary,
and q refers to number of moving average terms. Results obtained from ARIMA model showed significant decrease cases in
Australia; stable case for China and rising cases has been observed in other countries.
Conclusion:
This study tried their best at predicting the possible proliferate of COVID-19, although spreading significantly
depends upon the various control and measurement policy taken by each country.