- - - Department of Mathematics, College of Science, University of Baghdad, Iraq
- - - Department of Mathematics, College of Science, University of Baghdad, Iraq

In this paper, the time series data for the number of deaths from Coronavirus (COVID-۱۹) patients in Iraq were analyzed for the period from ۴/۳/۲۰۲۰ to ۱۸/۲/۲۰۲۱. ARCH, GARCH, and TGARCH models were applied due to the changing volatility of the series leading to a heteroscedastic variance. The appropriate models for the series were diagnosed and the best model was chosen and used for forecasting by the exponential smoothing methods. The comparison criterion used was the Root Mean Squared Error and the Sum of Squared Residuals. The most appropriate model for modeling and forecasting the Coronavirus deaths series in Iraq was diagnosed as TGARCH (۱,۱). Finally, the method of Holt-winter-additive forecasting was the best method among the

COVID-۱۹, time series, Volatility, heteroscedastic variance, Garch, ARCH, TGARCH