Analysis of twenty-week time-series of confirmed cases of New Coronavirus COVID-19 and their simple short-term prediction for Georgia and Neighboring Countries (Armenia, Azerbaijan, Turkey, Russia) in amid of a global pandemic

Amiranashvili, A. G.; Khazaradze, K. R.; Japaridze, N. D.

Results of a comparative statistical analysis of the daily data associated with New coronavirus COVID-19 infection of confirmed cases ([C]) of the population in Georgia (GEO), Armenia (ARM), Azerbaijan (AZE), Turkey (TUR) and Russia (RUS) amid a global pandemic (WLD) in the period from March 14 to July 31, 2020 are presented. The analysis of data is carried out with the use of the standard statistical analysis methods of random events and methods of mathematical statistics for the non-accidental time-series of observations. In particular, a correlation and autocorrelation analysis of the observational data was carried out, the periodicity in the time- series of [C] were revealed, the calculation of the interval prediction values of [C] taking into account the periodicity in the time-series of observations from August 1 to 31, 2020 (ARM, AZE) and from August 1 to September 11, 2020 (WLD, GEO, TUR, RUS) were carried out. Comparison of real and calculated predictions data on [C] in the study sites from August 1 to August 31, 2020 is carried out. It was found that daily, monthly and mean weekly real values of [C] for all the studied locations practically fall into the 99% confidence interval of the predicted values of [C] for the specified time period. A dangerous situation with the spread of coronavirus infection may arise when the mean weekly values of [C] of the 99% upper level of the forecast confidence interval are exceeded within 1-2 weeks. Favorable - when the mean weekly values of [C] decrease below 99% of the lower level of the forecast confidence interval.