Time series analysis of the spread of COVID-19 infection in Bulgaria

ABSTRACT

The number of confirmed, deaths and recovered cases of Covid-19 in.the period 08.03.2020-29.04.2021 in.Bulgaria are considered. Various smoothing techniques have been used to highlight the trend in data change. Confidence intervals are obtained for daily and weekly deaths after 14 days based on confirmed cases to date. The Box-Cox transformed confirmed cases were modeled by regression with respect to three dummy variables related to working days and holidays, with errors following ARIMA(1,1,2)(2,0,0)7 model. For Box-Cox transformed deaths, three other dummy variables and lag 16 of transformed and smoothed confirmed cases were used. The regression errors follow ARIMA(1,1,2) model in which the MA(1) coefficient is set to 0. Fourteen daily forecasts are obtained which agree well with the respective test data sets. © 2022 Author(s).