Forecasting Novel COVID 19 Virus Effect on Indian Population in Terms of Confirmed, Recovered, Death and Active Cases Using a Classical Data Driven Method in R

Abstract

The government of India has implemented nationwide lockdown on 25th March, 2020 following World Health Organization declaration of the coronavirus disease 2019 (Covid19) as pandemic on 11th March, 2020. The current lockdown has been planned till 17th May, 2020, subject to extension based on the COVID-19 affected population figures. In the present study, we have considered a comprehensive COVID-19 database pertaining to India which encompasses confirmed, recovered, death and active cases in cumulative form, from the first registered case in India on 30th January, 2020 to 4th May, 2020, and have employed Auto Regressive Integrated Moving Average (ARIMA) in the essence of data driven approach followed by validation based on Akaike information criterion (AIC) statistics for model prediction and forecasting the tentative numbers of affected population till 17th May, 2020 and 30 days beyond. The proposed methodology has been developed in R 3.6.3 using R Studio (version 1.2.5033) as Integrated Development Environment. The results obtained are a clear indicative that the current tenure of the lockdown should be extended for a considerable period of time to ensure the safety of the Indian population against the novel COVID-19 virus.