Page 135 - MI-2-3

Microbes & Immunity Statistical modeling of COVID-19 trends

of COVID-19 cases. The results reveal significant spatial Consent for publication
clusters of high infection rates, suggesting that local
factors—such as public health policies, population density, Not applicable.
and mobility patterns—play crucial roles in the spread Availability of data
of the virus. These findings suggest that a one-size-fits-
35
all approach is insufficient for managing the pandemic, All datasets used in this study are listed in Table 1.
highlighting the necessity of region-specific strategies. References
In conclusion, while the ARIMA and ARIMAX models 1. Lai CC, Shih TP, Ko WC, Tang HJ, Hsueh PR. Severe acute
serve as valuable tools for understanding and predicting respiratory syndrome coronavirus 2 (SARS-CoV-2) and
COVID-19 trends, their limitations underscore the need coronavirus disease-2019 (COVID-19): The epidemic and
for more complex models that can effectively capture the the challenges. Int J Antimicrob Agents. 2020;55(3):105924.
dynamic and non-linear nature of the pandemic. The doi: 10.1016/j.ijantimicag.2020.105924
47
multiple regression analysis highlights the crucial role of
socioeconomic factors in determining COVID-19 case 2. Adhikari R, Agrawal RK. An introductory study on time
numbers, suggesting that public health interventions series modeling and forecasting. arXiv [Preprint]; 2013.
should be tailored to address these disparities. The doi: 10.48550/arXiv.1302.6613
spatial autocorrelation analysis further emphasizes the 3. Benvenuto D, Giovanetti M, Vassallo L, Angeletti S,
importance of region-specific strategies in controlling Ciccozzi M. Application of the ARIMA model on the
the spread of the virus. Future research should focus on COVID-2019 epidemic dataset. Data Brief. 2020;29:105340.
refining these models, incorporating more real-time doi: 10.1016/j.dib.2020.105340
data, and improving the granularity of spatial analyses
to enhance their predictive accuracy and applicability in 4. Petropoulos F, Makridakis S. Forecasting the novel
public health decision-making. Additionally, the effect coronavirus COVID-19. PLoS One. 2020;15(3):e0231236.
of vaccination on COVID-19 case numbers, as explored doi: 10.1371/journal.pone.0231236
through various statistical techniques, highlights the 5. Bontempi E, Vergalli S, Squazzoni F. Understanding
critical role of timely and effective vaccination efforts in COVID-19 diffusion requires an interdisciplinary, multi-
controlling the pandemic. However, the variability in dimensional approach. Environ Res. 2020;188:109814.
outcomes across different regions suggests that a tailored, doi: 10.1016/j.envres.2020.109814
region-specific approach is essential for optimizing public 6. Paltiel AD, Zheng A, Schwartz JL. Speed versus efficacy:
health responses.
Quantifying potential tradeoffs in COVID-19 vaccine
Acknowledgments deployment. Ann Intern Med. 2021;174(4):568-570.
doi: 10.7326/M20-7866
I would like to express my sincere gratitude to my
supervisor, Dr. Wen Zhang, for his invaluable guidance, 7. Islam N, Khunti K, Dambha-Miller H, Kawachi I, Marmot M.
insightful feedback, and continuous support throughout COVID-19 mortality: A complex interplay of sex, gender
and ethnicity. Eur J Public Health. 2020;30(5):847-848.
the entire process of my research and thesis writing.
His expertise, patience, and encouragement have been doi: 10.1093/eurpub/ckaa150
instrumental in the successful completion of this work. 8. Bambra C, Riordan R, Ford J, Matthews F. The COVID-19
pandemic and health inequalities. J Epidemiol Community
Funding Health. 2020;74(11):964-968.
None. doi: 10.1136/jech-2020-214401

Conflict of interest 9. Box GE, Jenkins GM, Reinsel GC, Ljung GM. Time Series
th
Analysis: Forecasting and Control. 5 ed. United States: John
The author declares no conflicts of interest. Wiley and Sons; 2015.
10. Hamilton JD. Time Series Analysis. United States: Princeton
Author contributions University Press; 1994.
This is a single-authored article. 11. Dickey DA, Fuller WA. Distribution of the estimators for
autoregressive time series with a unit root. J Am Stat Assoc.
Ethics approval and consent to participate 1979;74(366a):427-431.
Not applicable. doi: 10.1080/01621459.1979.10482531

Volume 2 Issue 3 (2025) 127 doi: 10.36922/MI025040007