Modelling Long-Memory Dynamics in Indian COVID-19 Data with ARFIMA Models
Keywords:
integration, Comparative, Maximum, predictionAbstract
This study evaluates the feasibility and effectiveness of the Auto Regressive Fractionally Integrated Moving Average (ARFIMA) model in capturing the long-memory dynamics of COVID-19 new cases time series data in India. By employing ARFIMA modeling, the research identifies persistent long-term dependencies characterized by fractional differencing parameters. The findings indicate that conventional short-memory ARMA models fail to adequately account for the non-stationarity and volatility observed across multiple waves of COVID-19 infections. The estimated fractional differencing parameter of 0.5 confirms significant long-memory characteristics, supported by high autocorrelation and non-normal residuals, as revealed by diagnostic tests. Short-term and subset forecasting suggest a stabilizing trend towards endemic patterns, though prediction uncertainty increases over time. Comparative analysis shows a slight advantage of Nonlinear Least Squares estimation over Maximum Likelihood methods. The study concludes that ARFIMA models effectively capture the long-memory properties of pandemic data, but further refinements and integration with hybrid approaches are needed to enhance forecasting accuracy and inform policy decisions.
Downloads
References
https://stats.stackexchange.com/questions/408871/interpreting-qq-plot-from-arima-residuals
Demetris, K. Climate change, the Hurst phenomenon, and hydrological statistics. Hydrological Sciences–Journal–des Sciences Hydrologiques, 2003 48(1) February 2003.
M.A. Sanchez Granero, M.A.; Trinidad Segovia, J.E.; García Pérez, J. Some comments on Hurst exponent and the long memory processes on capital markets. Physica A 387 (2008) 5543–5551.
Mignon, V. Hurst's exponent estimation methods. Application to stock market profitability. In: Economy and Forecasting, n° 132-133, 1998-1-2. Pp. 193-214.
Angela D’Elia, A.; Piccolo, D. Maximum likelihood estimation of ARFIMA models with a Box-Coxtransformation. Statistical Methods & Applications (2003) 12: 259–275. DOI: 10.1007/s10260-003-0064-0.
Forecasting COVID-19 new cases in Algeria using Autoregressive fractionallyintegrated moving average Models (ARFIMA), Balah Belkacem, Messaoud DJEDDOU, https://www.researchgate.net/publication/341251558
Mostafaei, H. Using SARFIMA Model to Study and Predict the Iran’s Oil Supply. International Journal ofEnergy Economics and Policy. Vol. 2, No. 1, 2012, pp.41-49 ISSN: 2146-4553.
Corduas, M. Preliminary Estimation of ARFIMA Models. Chapte. Dipartimento di ScienzeStatistiche, 2000, University of Naples Federico II, Napoli, Italy. DOI: 10.1007/978-3-642-57678-2_28
Cao, G.; He, L-Y.; Cao, J. Multifractal Detrended Analysis Method and Its Application in Financial Markets.2018, Springer. 255 pages. ISBN 978-981-10-7916-0.
Moeeni, H.; Bonakdari, H.; Seyed Ehsan Fatemi, S.E.; Zaji, A.H. Assessment of Stochastic Models and aHybrid Artificial Neural Network-Genetic Algorithm Method in Forecasting Monthly Reservoir Inflow, IndianNational Academy of Engineering, INAE Lett (2017) 2:13–23 DOI 10.1007/s41403-017-0017-9
Mason, D.M. The Hurst phenomenon and the rescaled range statistic. Stochastic Processes and theirApplications 126 (2016) 3790–3807.
Tong, S.; Lai, Q.; Zhang, J.; Bao, Y.; Lusi, A.; Ma, Q.; Li. X.; Zhang, F. Spatiotemporal drought variabilityon the Mongolian Plateau from 1980–2014 based on the SPEI-PM, intensity analysis and Hurst exponent.Science of the Total Environment 615 (2018) 1557–1565.
Aouad, H.S.; A.H.; Taouli, M.K.; Benbouziane, M. Modeling the behavior of the Algerian dinar exchangerate: an empirical investigation using the ARFIMA method. International Research Journal of Finance andEconomics, 2012, Issue 87 ISSN 1450-2887.
Grech, D.; Mazur, Z. Can one make any crash prediction in nance using the local Hurst exponent idea.Physica A 336 (2004) 133 – 145. doi:10.1016/j.physa.2004.01.018.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
