Best selected forecasting models for COVID-19 pandemic
This study sought to identify the most accurate forecasting models for COVID-19-confirmed cases, deaths, and recovered patients in Pakistan. For COVID-19, time series data are available from 16 April to 15 August 2021 from the Ministry of National Health Services Regulation and Coordination’s health...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2022-12-01
|
Series: | Open Physics |
Subjects: | |
Online Access: | https://doi.org/10.1515/phys-2022-0218 |
_version_ | 1797294615872667648 |
---|---|
author | Fayomi Aisha Nasir Jamal Abdul Algarni Ali Rasool Muhammad Shoaib Jamal Farrukh Chesneau Christophe |
author_facet | Fayomi Aisha Nasir Jamal Abdul Algarni Ali Rasool Muhammad Shoaib Jamal Farrukh Chesneau Christophe |
author_sort | Fayomi Aisha |
collection | DOAJ |
description | This study sought to identify the most accurate forecasting models for COVID-19-confirmed cases, deaths, and recovered patients in Pakistan. For COVID-19, time series data are available from 16 April to 15 August 2021 from the Ministry of National Health Services Regulation and Coordination’s health advice portal. Descriptive as well as time series models, autoregressive integrated moving average, exponential smoothing models (Brown, Holt, and Winters), neural networks, and Error, Trend, Seasonal (ETS) models were applied. The analysis was carried out using the R coding language. The descriptive analysis shows that the average number of confirmed cases, COVID-19-related deaths, and recovered patients reported each day were 2,916, 69.43, and 2,772, respectively. The highest number of COVID-19 confirmed cases and fatalities per day, however, were recorded on April 17, 2021 and April 27, 2021, respectively. ETS (M, N, M), neural network, nonlinear autoregressive (NNAR) (3, 1, 2), and NNAR (8, 1, 4) forecasting models were found to be the best among all other competing models for the reported confirmed cases, deaths, and recovered patients, respectively. COVID-19-confirmed outbreaks, deaths, and recovered patients were predicted to rise on average by around 0.75, 5.08, and 19.11% daily. These statistical results will serve as a guide for disease management and control. |
first_indexed | 2024-03-07T21:33:44Z |
format | Article |
id | doaj.art-80ba6f86928f47d5a057f13f5a67a342 |
institution | Directory Open Access Journal |
issn | 2391-5471 |
language | English |
last_indexed | 2024-03-07T21:33:44Z |
publishDate | 2022-12-01 |
publisher | De Gruyter |
record_format | Article |
series | Open Physics |
spelling | doaj.art-80ba6f86928f47d5a057f13f5a67a3422024-02-26T14:29:02ZengDe GruyterOpen Physics2391-54712022-12-012011303131210.1515/phys-2022-0218Best selected forecasting models for COVID-19 pandemicFayomi Aisha0Nasir Jamal Abdul1Algarni Ali2Rasool Muhammad Shoaib3Jamal Farrukh4Chesneau Christophe5Faculty of Science, Department of Statistics, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Statistics, Government College University Lahore, Lahore, PakistanFaculty of Science, Department of Statistics, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Pediatrics, THQ Hospital, Ferozewala, Lahore, PakistanDepartment of Statistics, The Islamia University of Bahawalpur, Bahawalpur, PakistanDépartement de Mathématiques, Université de Caen Normandie, LMNO, Campus II, Science 3, 14032, Caen, FranceThis study sought to identify the most accurate forecasting models for COVID-19-confirmed cases, deaths, and recovered patients in Pakistan. For COVID-19, time series data are available from 16 April to 15 August 2021 from the Ministry of National Health Services Regulation and Coordination’s health advice portal. Descriptive as well as time series models, autoregressive integrated moving average, exponential smoothing models (Brown, Holt, and Winters), neural networks, and Error, Trend, Seasonal (ETS) models were applied. The analysis was carried out using the R coding language. The descriptive analysis shows that the average number of confirmed cases, COVID-19-related deaths, and recovered patients reported each day were 2,916, 69.43, and 2,772, respectively. The highest number of COVID-19 confirmed cases and fatalities per day, however, were recorded on April 17, 2021 and April 27, 2021, respectively. ETS (M, N, M), neural network, nonlinear autoregressive (NNAR) (3, 1, 2), and NNAR (8, 1, 4) forecasting models were found to be the best among all other competing models for the reported confirmed cases, deaths, and recovered patients, respectively. COVID-19-confirmed outbreaks, deaths, and recovered patients were predicted to rise on average by around 0.75, 5.08, and 19.11% daily. These statistical results will serve as a guide for disease management and control.https://doi.org/10.1515/phys-2022-0218covid-19forecasting modelspakistantime series analysis |
spellingShingle | Fayomi Aisha Nasir Jamal Abdul Algarni Ali Rasool Muhammad Shoaib Jamal Farrukh Chesneau Christophe Best selected forecasting models for COVID-19 pandemic Open Physics covid-19 forecasting models pakistan time series analysis |
title | Best selected forecasting models for COVID-19 pandemic |
title_full | Best selected forecasting models for COVID-19 pandemic |
title_fullStr | Best selected forecasting models for COVID-19 pandemic |
title_full_unstemmed | Best selected forecasting models for COVID-19 pandemic |
title_short | Best selected forecasting models for COVID-19 pandemic |
title_sort | best selected forecasting models for covid 19 pandemic |
topic | covid-19 forecasting models pakistan time series analysis |
url | https://doi.org/10.1515/phys-2022-0218 |
work_keys_str_mv | AT fayomiaisha bestselectedforecastingmodelsforcovid19pandemic AT nasirjamalabdul bestselectedforecastingmodelsforcovid19pandemic AT algarniali bestselectedforecastingmodelsforcovid19pandemic AT rasoolmuhammadshoaib bestselectedforecastingmodelsforcovid19pandemic AT jamalfarrukh bestselectedforecastingmodelsforcovid19pandemic AT chesneauchristophe bestselectedforecastingmodelsforcovid19pandemic |