Conway-Maxwell-Poisson model fitting to HFMD data in Malaysia
DOI:
https://doi.org/10.15282/daam.v6i1.11140Keywords:
HFMD, Over-dispersed, Time series, MalaysiaAbstract
Since the first Hand, Foot and Mouth Disease (HFMD) outbreak occurred in Sarawak, Malaysia in 1997, the number of reported cases has remained in a cyclical pattern. Numerous HFMD research involve clinical and laboratory findings. However, there is limited research that models the distribution of the HFMD dataset in Malaysia using a count data model fitting. This study aims to demonstrate the flexibility of the Conway-Maxwell-Poisson (COM-Poisson) regression model. All daily reported cases of HFMD from 2009 to 2019 were analysed and presented by each state in Malaysia. A normal Poisson was extensively used, but it has limitations in terms of the equi-dispersion assumption. Thus, the performance of the COM-Poisson model was investigated and compared to the Poisson model by looking at the goodness of fit (log-likelihood, AIC, and BIC) test values. The results showed that COM-Poisson models fit the HFMD dataset well with lower AIC and BIC values compared to the Poisson model. The parameter coefficients' estimated values also indicated smaller values than in the Poisson model. Given the versatility of the COM-Poisson distribution, it is effective for statistical applications and procedures, such as modelling count data. In addition, the potential for related research was also being examined to improve the accuracy of the predictive model.
References
[1] Chan LG, Parashar UD, Lye MS, Ong FG, Zaki SR, Alexander JP, Ho KK, Han LL, Pallansch MA, Suleiman AB, Jegathesan M. Deaths of children during an outbreak of hand, foot, and mouth disease in Sarawak, Malaysia: clinical and pathological characteristics of the disease. Clinical Infectious Diseases. 2000 1;31(3):678-83.
[2] Ministry of Health (Malaysia). Prevention and Control of Infectious Diseases Act 1988: Incorporating latest amendment – P.U.(A) 374/2006. 2006.
[3] Ministry of Health (Malaysia). Health Facts. 2002. Available from: https://www.moh.gov.my/index.php/-pages/view/58?mid=19
[4] Sham NM, Krishnarajah I, Shitan M, Lye MS. Time series modelon hand, foot and mouth disease in Sarawak, Malaysia. Asian Pacific Journal of Tropical Disease. 2014;4(6):469-72.
[5] Gu J, Liang L, Song H, Kong Y, Ma R, Hou Y, Zhao J, Liu J, He N, Zhang Y. A method for hand-foot-mouth disease prediction using GeoDetector and LSTM model in Guangxi, China. Scientific Reports. 2019;9(1):17928.
[6] Liu L, Luan RS, Yin F, Zhu XP, Lü Q. Predicting the incidence of hand, foot and mouth disease in Sichuan province, China using the ARIMA model. Epidemiology & Infection. 2016;144(1):144-51.
[7] Tian CW, Wang H, Luo XM. Time-series modelling and forecasting of hand, foot and mouth disease cases in China from 2008 to 2018. Epidemiology & Infection. 2019;147:e82.
[8] Yu G, Feng H, Feng S, Zhao J, Xu J. Forecasting hand-foot-and-mouth disease cases using wavelet-based SARIMA–NNAR hybrid model. PLoS one. 2021;16(2):e0246673.
[9] Conway RI. A queueing model with state dependent service rate. Journal of Industrial Engineering. 1961;12:132.
[10] Guikema SD, Goffelt JP. A flexible count data regression model for risk analysis. Risk Analysis: An International Journal. 2008;28(1):213-23.
[11] Akaike H. Information theory and an extension of the maximum likelihood principle. In: Petrov BN, Csaki F, editors. Proceedings of the 2nd International Symposium on Information Theory. Budapest: Akademiai Kiado; 1973.
[12] Schwarz G. Estimating the dimension of a model. The Annals of Statistics. 1978:461-4.
[13] Acquah H. On the comparison of Akaike information criterion and consistent Akaike information criterion in selection of an asymmetric price relationship: Bootstrap simulation results. AGRIS on-line Papers in Economics and Informatics. 2013;5(1):3-9.
[14] Bozdogan H. Model selection and Akaike's information criterion (AIC): The general theory and its analytical extensions. Psychometrika. 1987;52(3):345-70.
[15] Zucchini W. An introduction to model selection. Journal of mathematical psychology. 2000;44(1):41-61.
[16] R Core Team. R: A language and environment for statistical computing. 2020.
[17] Department of Statistics Malaysia. MyCensus 2020. 2023.
[18] Hayati M, Sadik K, Kurnia A. Conwey-Maxwell Poisson distribution: approach for over-and-under-dispersed count data modelling. In IOP Conference Series: Earth and Environmental Science 2018 (vol. 187, no. 1, p. 012039). IOP Publishing.
[19] Santana RA, Conceição KS, Diniz CA, Andrade MG. Type I multivariate zero‐inflated COM–Poisson regression model. Biometrical Journal. 2022;64(3):481-505.
[20] Li X, Dey DK. Estimation of COVID-19 mortality in the United States using Spatio-temporal Conway Maxwell Poisson model. Spatial Statistics. 2022;49:100542.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
