Initial Growth Rate and Model Performance for COVID-19 in Nigeria

Abstract

While numerous statistical models have been used to analyze the spread of COVID-19 in Nigeria, focusing on factors such as active cases and deaths, there is a gap in understanding the impact of initial parameter choices within these models. This study investigates the impact of initial growth rate parameter choices on the performance of different population growth models in fitting cumulative COVID-19 cases in Nigeria. By comparing Gompertz, logistic, Richard’s, modified Gompertz and Morgan-Mercer-Flodin models, the study aims to determine the most appropriate model for analyzing the spread of the disease. Using data from Our World in Data (OWID), the models were fitted to the S-shaped curve observed in the cumulative case data. The performance of the models was evaluated using convergence efficiency, measured by the number of iterations required to converge and the convergence tolerance achieved, and model fit criteria such as log-likelihood, Bayesian Information Criterion (BIC) and Akaike Information Criterion (AIC). The results show that the Gompertz model consistently outperforms other models in terms of both efficiency and convergence tolerance. This suggests that the Gompertz model is a more appropriate choice for future research using population growth models to analyze the spread and impact of infectious diseases in Nigeria.