Probabilistic Analysis of Covid-19 Pandemic in Kenya Using Markov Chain

Abstract

Since the inception of Covid-19 in China, the economies around the world have been on the turmoil. This is because China has a direct correlation with most economies in the world; they depend on it directly or indirectly. On 13th March, 2020 the first case of COVID-19 in Kenya a 27-year-old Kenyan woman who traveled from the US via London, was confirmed. The Kenyan government identified and isolated a number of people who had come into contact with the first case. On 15 March 2020, the president of Kenya directed that a number of measures be taken to curb COVID-19, some of those measures included; dusk to dawn curfew, secession of movement and mandatory quarantine of suspected cases. Based on the available literature, probabilistic predictions using steady state Markov chain allow to assess the uncertainty of the COVID-19 comprehensively. Therefore they are preferable to forecasts for the mean or median COVID-19 only. The probabilistic COVID-19 predictions allow to derive probabilistic forecasts for the number of patients who are still at the ICU at a certain day in future. This may be useful for planning purposes. From the probabilities for single patients, one may compute the probability that any given number of patients is still at the ICU after t days. However, in Kenya there is scanty information on analysis of COVID-19 using steady state Markov Chain. The aim of this study was therefore be to carry out probabilistic analysis of COVID-19 pandemic in Kenya using Markov chain. The study was a literature based, in which the researcher reviewed surveys books, scholarly journals, and other secondary sources relevant to the current study topic. The findings revealed that one of the most important uses of steady state Markov chain in analyzing COVID-19 pandemic situation in Kenya is that it compares performances for different states of affairs and courses of action within the health sector, by using system steady state performance measurements. The study concludes that steady state Markov chain is beneficial in simulating the corona infection in numerous stages. It is thus recommended that there is need for policy-makers to seek regional and global solutions to COVID-19 disease instead of limited solutions within the country. Keywords: Steady State, Markov chain, COVID-19 Pandemic, Transition Matrix