|
Modeling daily COVID-19 time series data using ARIMA models: A multi-country analysis
|
M. Maroufi   , K. Zare , M. R. Mahmoudi , D. Jamali , Z. Sajjadian |
| Department of Statistics, Marv.C., Islamic Azad University, Marvdasht, Iran |
|
|
Abstract: (6 Views) |
Modeling the temporal dynamics of COVID-19 is important for understanding the progression of the pandemic. This study fitted Autoregressive Integrated Moving Average (ARIMA) models to the daily numbers of confirmed COVID-19 cases and deaths in seven countries: the USA, Spain, the UK, Italy, Iran, Germany, and France. The dataset covered the period from February to April 2020. Model structures were identified using the autocorrelation function (ACF) and partial autocorrelation function (PACF), and the final models were selected based on the corrected Akaike Information Criterion (AICC) and Bayesian Information Criterion (BIC). Model adequacy was evaluated using residual diagnostics, including ACF/PACF plots and the Ljung–Box test, which showed no significant residual autocorrelation for the selected models. The results indicate that ARIMA models provide an adequate statistical framework for describing the temporal dependence structure of daily COVID-19 time series and offer a basis for further short-term analyses.
|
|
| Keywords: COVID-19, Autoregressive Integrated Moving Average (ARIMA), Time Series Analysis. |
|
|
Full-Text [PDF 483 kb]
(3 Downloads)
|
Type of Study: Research |
Subject:
General
Received: 2025/11/2 | Accepted: 2025/12/14 | Published: 2026/01/11
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
