Open AccessAn Analysis of COVID-19 Cases in Nepal: A Modeling Approach
Author(s) -
Surendra Raj Nepal
Publication year - 2020
Publication title -
journal of institute of science and technology
Language(s) - English
Resource type - Journals
eISSN - 2467-9240
pISSN - 2467-9062
DOI - 10.3126/jist.v25i2.33744
Subject(s) - autoregressive integrated moving average , gompertz function , covid-19 , statistics , logistic regression , confidence interval , demography , medicine , mathematics , time series , disease , sociology , infectious disease (medical specialty)
Unlike previous coronaviruses infections, COVID-19 has badly affected not only the health of people but also the socioeconomic activities of Nepal. It would help the government of Nepal to manage this crisis if a proper mechanism to predict COVID cases has been developed. This study aims to look for patterns of confirmed, recovery and death cases. Moreover, it tries to check whether Gompertz and Logistic model would be able to read the patterns of total confirmed and death cases. It also forecasts the total number of confirmed as well as death cases. Data from January 23, 2020 to October 30, 2020 obtained from the website of Wikipedia are used for analysis. Gompertz and Logistic models were fitted to the total number of confirmed and death cases and models are compared based on various criteria. Besides, an automatic ARIMA model was used to predict cumulative confirmed and death cases and the accuracy of the model was also checked. ARIMA model forecasted 347,812 confirmed cases and 1,754 death cases till December 31, 2020. At 95 % confidence interval, the confirmed cases were expected between 273,889 and 421,734 whereas death cases were estimated from 1,387 to 2,119. Both models were fitted well in both total confirmed cases and total death cases. It was found that the Logistic model fits better in total confirmed cases whereas in total death cases, the Gompertz model was better. ARIMA model precisely forecasted the number of confirmed and death cases.