Analysis the Increment of COVID-19 Cases in Indonesia with One of Multivariate Markov Chain Model Parameter

Abstract

The global cases of COVID-19 pandemic extensively increase as in Indonesia as the first two confirmed (positive) cases were reported in 2nd of March 2020 and followed by the first mortality case in 9 days afterwards, 11th of March 2020. In latest situation, the last data collection by author in 5th of November 2020 14,348 died and 425,796 COVID-19 confirmed cases were recorded. Therefore, in this study the author will construct a Multivariate Markov-Chain Model to estimate the increase in COVID-19 patients for confirmed, recovered, and died cases. Multivariate Markov chain is popular model for forecasting by observing current state in various applications. This model is compatible with 3 data sequences (patient types) defined as recovered patient, confirmed, and died with 6 conditions (zero, least, less, fair, ample, and massive). As the result, this study shows transition probability matrix with 3x3 dimension where each element containing 6x6 conditions. The highest transition probability value for the increment of COVID-19 cases in Indonesia on March 11 to November 5, 2020, occurred in a transition from confirmed to confirmed patient with conditions from ample to ample, which had the highest probability value 0.8571 and the highest frequency 78 times.