Modeling and Forecasting COVID-19 Incidence Rates: A Time Series Analysis of Acute Respiratory Infections (ARI) in France Since Surveillance Initiation

Yıl 2023, Cilt: 7 Sayı: 3, 117 - 130, 19.01.2024

Hanife Taylan Selamlar

https://doi.org/10.33716/bmedj.1415849

Öz

Objective: This study aims to address the challenges of planning and managing the trajectory of the COVID-19 pandemic by evaluating the predictive abilities of three distinct forecasting models. The primary focus is on the ATA univariate forecasting method, ARIMA (AutoRegressive Integrated Moving Average), and ETS (Error-Trend-Seasonality) models. These models are applied to a meticulously collected dataset comprising Acute Respiratory Infections (ARI) incidence rates in France, systematically collected since the initiation of surveillance.
Methods: The purpose of the study was to conduct a comprehensive evaluation of forecasting models using the selected dataset to achieve its objective. The focus was on comparing the accuracy and performance of ATA univariate forecasting, ARIMA, and ETS models in predicting COVID-19 incidence rates. Additionally, the study incorporated a combination approach proven to be effective in enhancing forecasting performance.
Results: According to the results obtained regarding forecast performance, the univariate models indicate that the ATA method exhibits the highest performance, while observations reveal that combinations of ATA and ARIMA methods enhance forecast accuracy.
Conclusions: In summary, the most accurate approach for forecasting future Covid-19 incidence rates, specifically those derived from Acute Respiratory Infections (ARI), has been a combination of the high-accuracy methods ATA and ARIMA. These findings enhance our understanding of the trajectory of the pandemic, providing a foundation for strategic planning and effective management.

Anahtar Kelimeler

Forecasting, Covid 19, ATAForecasting, ETS, ARIMA, Acute Respiratory Infections (ARI)

COVID-19 İnsidans Oranlarını Modelleme ve Öngörümleme: Fransa'da Gözetim Başlangıcından Beri Akut Solunum Enfeksiyonları (ARI) Zaman Serisi Analizi

Öz

Amaç: Bu çalışma, COVID-19 pandemisinin trajedisini planlama ve yönetme zorluklarına karşı üç farklı tahmin modelinin öngörü yeteneklerini değerlendirerek ele almayı amaçlamaktadır. Temel odak noktası, ATA tek değişkenli tahmin yöntemi, ARIMA (OtoRegresif Entegre Hareketli Ortalama) ve ETS (Hata-Eğilim-Mevsimlilik) modelleridir. Bu modeller, Fransa'da gözetimin başlangıcından bu yana titizlikle toplanan Akut Solunum Enfeksiyonları (ARI) insidans oranlarını içeren bir veri setine uygulanmıştır.
Yöntem: Çalışmanın amacına ulaşmak için seçilen veri setini kullanarak tahmin modellerinin kapsamlı bir değerlendirmesini yapmak amaçlanmıştır. Odak noktası, COVID-19 insidans oranlarını tahmin etmede ATA tek değişkenli tahmin, ARIMA ve ETS modellerinin doğruluğunu ve performansını karşılaştırmaktır. Ayrıca, çalışma, tahmin performansını artırmada etkili olduğu kanıtlanmış bir kombinasyon yaklaşımını da içermiştir.
Bulgular: Tahmin performansına ilişkin elde edilen sonuçlara göre, tek değişkenli modeller, ATA yönteminin en yüksek performansı sergilediğini gösterirken gözlemler, ATA ve ARIMA yöntemlerinin kombinasyonlarının tahmin doğruluğunu artırdığını göstermektedir.
Sonuç: Özetle, gelecekteki Covid-19 insidans oranlarını, özellikle Akut Solunum Enfeksiyonları (ASE) kaynaklı olanları tahmin etmede en doğru yaklaşım, ATA ve ARIMA gibi yüksek doğrulukta yöntemlerin kombinasyonu olmuştur. Bu bulgular, pandeminin seyrine dair anlayışımızı artırarak stratejik planlama ve etkili yönetim için bir temel sağlamaktadır.

Anahtar Kelimeler

Öngörü, Covid19, ATAÖngörü, ETS, ARIMA, Akut Solunum Enfeksiyonları (ASE)

Kaynakça

• Yapar G, Modified simple exponential smoothing, Hacettepe Journal of 235 Mathematics and Statistics 2018:47 (3),741–754.
• Yapar G, I. Yavuz I, Selamlar Taylan H, Why and how does exponential smoothing fail? an in depth comparison of ata-simple and simple exponential smoothing., Turkish Journal of Forecasting 2017:1 (1), 30–39.
• Yapar G, Capar S, Selamlar Taylan H, Yavuz I, Modified holt’s linear trend method, Hacettepe Journal of Mathematics and Statistics 2018: 47 (5), 1394–1403.
• Yapar G, Selamlar Taylan H, Capar S, Yavuz I, Ata method, Hacettepe Journal of Mathematics and Statistics 2019: 48 (6), 1838–1844.
• Yilmaz Ekiz T, G. Yapar G, Yavuz I, Comparison of ata method and croston based methods on forecasting of intermittent demand, Mugla Journal of Science and Technology 2019: 5 (2), 49 – 55.
• Cetin B, Yavuz I, Comparison of forecast accuracy of ata and exponential smoothing, Journal of Applied Statistics (2020) 1–11.
• Capar S, Selamlar Taylan H, Yavuz I, Taylan A S, Yapar G, Ata method’s performance in the m4 competition, Hacettepe Journal of Mathematics and Statistics 2023:52 (1), 268 – 276. doi:10.15672/hujms.1018362.
• Taylan A, Yapar G, Selamlar Taylan H, Automatic time series forecasting with ata method in r: Ataforecasting package, R J. 13 (2021) 441. URL https://api.semanticscholar.org/CorpusID:245259120
• Akanksha U, Neha S., Jayanti S. Comparison of exponential smoothing and ARIMA time series models for forecasting COVID-19 cases: a secondary data analysis. International Journal of Research in Medical Sciences, 2023, doi: 10.18203/2320-6012.ijrms20231344
• Xiuling L., Mon L, Wang X, Xie W, Su H, LiuQian., Jiangping Z. Application of Autoregressive Moving Average Model in the Prediction of COVID-19 of China. Asian Journal of Probability and Statistics, 2022, doi: 10.9734/ajpas/2022/v20i3433.
• Suraj, Singh, Nagvanshi., Charu, Agarwal. Nonstationary time series forecasting using optimized-EVDHM-ARIMA for COVID-19. Frontiers in big data, 2023, doi: 10.3389/fdata.2023.1081639.
• Rachasak, Somyanonthanakul., K., Warin., Watchara, Amasiri., Karicha, Mairiang., Chatchai, Mingmalairak., Wararit, Panichkitkosolkul., Krittin, Silanun., Thanaruk, Theeramunkong., Surapon, Nitikraipot., Siriwan, Suebnukarn. Forecasting COVID-19 cases using time series modeling and association rule mining. BMC Medical Research Methodology, 2022, doi: 10.1186/s12874-022-01755-x.
• Atchadé M. N. and Sokadjo Y. M., Overview and cross-validation of COVID-19 forecasting univariate models. alexandria engineering journal, 2022, doi: 10.1016/j.aej.2021.08.028.
• Box, G. E. P., Jenkins, G. M., & Reinsel, G. C. (1994). Time series analysis: forecasting and control. Holden-Day.
• Brockwell, P. J., & Davis, R. A. (2016). Introduction to time series and forecasting. Springer.
• Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts.
• Hyndman, R. J., & Khandakar, Y. Automatic time series forecasting: the forecast package for R. Journal of Statistical Software,2 018: 26(3), 1-22.
• Gardner Jr, E. S. Exponential smoothing: The state of the art. Journal of forecasting, 1985: 4(1), 1-28.
• A, Massey., C., Boennec., Claudia, X., Restrepo-Ortiz., Cherie, N., Blanchet., Samuel, Alizon., Mircea, T., Sofonea. Real-time forecasting of COVID-19-related hospital strain in France using a non-Markovian mechanistic model. medRxiv, 2023, doi: 10.1101/2023.02.21.23286228.
• Ferdin, J, Joseph J. Time series forecast of Covid 19 Pandemic Using Auto Recurrent Linear Regression. Maǧallaẗ al-abḥāṯ al-handasiyyaẗ, 2022, doi: 10.36909/jer.15425.
• S. S. Selvi, P. Barkur, N. Agarwal, A. Kumar and Y. Mishra, "Time Series based Models for Corona Data Analytics," 2022 Fourth International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT), Mandya, India, 2022, pp. 1-6, doi: 10.1109/ICERECT56837.2022.10059874.
• Christian, Selinger., Marc, Choisy., Samuel, Alizon. (2021). Predicting COVID-19 incidence in French hospitals using human contact network analytics.. International Journal of Infectious Diseases, doi: 10.1016/J.IJID.2021.08.029.
• Elena, Bobeica., Benny, Hartwig. (2021). The COVID-19 shock and challenges for time series models. doi: 10.2866/957422.