Open AccessARIMA Modelling and Forecasting of COVID-19 Daily Confirmed/Death Cases: A Case Study of Nigeria
Author(s) -
Essi Isaac Didi,
Kingdom Nwuju,
Etuk Ette Harrison
Publication year - 2021
Publication title -
asian journal of probability and statistics
Language(s) - English
Resource type - Journals
ISSN - 2582-0230
DOI - 10.9734/ajpas/2021/v12i330289
Subject(s) - autoregressive integrated moving average , covid-19 , work (physics) , pandemic , statistics , time series , demography , econometrics , geography , medicine , mathematics , disease , engineering , infectious disease (medical specialty) , sociology , mechanical engineering , pathology
Aims: The aim of this work is to develop suitable ARIMA models which can be sued to forecast daily confirmed/death cases of COVID-19 in Nigeria. This is subject to developing the model, checking them for suitability and carrying out eight months forecast, and making recommendations for the Nigerian Health sector.
Study Design: The study used daily confirmed and death cases of COVID-19 in Nigeria.
Methodology: This work covers times series data on the on the daily confirmed/death cases of COVID-19 in Nigeria, obtained from the Nigerian Centre for Disease Control (NDCD) from 21 March 2020 to 5 May 2020, covering a total of 51 data points. This work is geared towards developing a suitable Autoregressive Integrated Moving Average (ARIMA) models which can be used to forecast total daily confirmed/death cases of COVID-19 in Nigeria. Two adequate subset ARIMA (2, 2, 1) and AR (1) models for the confirmed/death cases, respectively, is fitted and discussed
Results: A forecast of 239 days – from 6th May 2020 to 31 December 2020 was conducted using the fitted models and we observed that the COVID19 data has an upward trend and is best forecasted within a short period.
Conclusion: Critical investigation into the rate of spread of COVID-19 pandemic has shown that, that the daily confirmed cases as well as death cases of the disease tends to follow an upward trend. This work aimed at developing a suitable ARIMA models which can be used to fit a most appropriate subsets to statistically forecast the actual number of confirmed cases as well as death cases of COVID-19 recorded in Nigeria for a period of 8 months.