Comparative Model Profiles of Covid-19 Occurrence In Nigeria

Abstract

In this article, we studied the comparative model profile of COVID-19 occurrence in Nigeria. The model was analyzed using Simple Regression Model in GRETL. The data adopted a non-stationary time series forecasting approach. We used the Mean Error (ME), Mean Square Error (MSE) and Root Mean Square Error (RMSE) to determine the performance measures that fit the COVID-19 confirmed cases Nigeria. The model was used Linear, Quadratic and Exponential Model to determine the best performing model for predicting COVID-19 cases. The findings showed that the RMSE value (84.60) for the linear model is the smallest compared to the RMSE of quadratic and exponential models with values 32492.29 and 136.32 respectively. This showed that the linear model was the best model that fitted COVID-19 cases in Nigeria both in terms of data fit and for prediction purposes. Moreover, the results also showed that the figure of the actual cases were above the predicted cases in all the three models, which could be as a result of some parameters like infectious contact rate or inaccurate COVID-19 cases data.