Robust Modelling of Coronavirus Cases in Egypt: Poisson INARCH and Negative Binomial INARCH

This study compares robust Poisson INARCH(P) models (more briefly: RP-INARCH) and negative binomial INARCH(p) RNB-INARCH) to fit the new daily confirmed cases for first wave of COVID 19 in Egypt. The estimation these is based on some modifications Conditional Maximum Likelihood Estimates (CMLE). simulation results show that RNB-INARCH more than RP-INARCH, but less efficient if data contain isolated or patched additive outliers terms bias calculation, whereby low-bias model robust. These are by application COVID-19 data. Akaike Information Criterion (AIC) also compared models.