Modelıng the effect of ınterventıon on covıd-19 prevalence ın kenya usıng logıstıc regressıon

The COVID-19 pandemic has caused great disruption worldwide. In connection to this, over 43 million people have confirmed diagnosis of the disease, and over 1 million people have died from it. Though it is well documented that a number of factors have been linked to the reduction of the risk of COVID-19 infection ranging from social distancing, mask wearing and washing of hands, Intervention could fight against the spread of the COVID-19 virus. In this paper, we used maximum likelihood estimation (MLE) method, to fit logistic regression model; first to data set without intervention then to data set with effect of intervention incorporated. This was done with an aim of determining the effect of intervention on COVID-19prevalence in Kenya. Model parameters were estimated by MLE method. AKaike’s information criteria (AIC) was used to compare the two models fitted to data so as to determine the better performing model. The study used data sets of 2019-2020(data obtained before vaccination intervention set in) and 2021-2023(data obtained after incorporation of vaccination intervention effect)COVID-19 data sets for Kenya ( from the Centre for Disease Control and Prevention (CDC)).The model fitted to the data set which contained the effect of Vaccination intervention gave a lower AIC value of 1293 compared to the one fitted to the data set which did not contain the effect of Vaccination intervention which gave AIC value of 1389. The logistic regression model fitted to data set containing the effect of vaccination intervention therefore had a better performance as indicated by the AIC value. The results of this study revealed a high prevalence of COVID-19 in the data set which had no effect of vaccination intervention. Whereas, a low prevalence of COVID – 19 was realized with data set which had effect of vaccination intervention incorporated. This indicates that the existence of vaccination in Kenya has played a significant role in reducing the prevalence of COVID-19 disease. The results of this study would be of much benefit to the health sector in monitoring and sensitizing people on the effect of Intervention on COVID-19 prevalence.