Forecasting the Proportion of Elders with Stress Problems in Khon Kaen Province
Keywords:
forecasting, the elderly, stress problem, Khon Kaen ProvinceAbstract
This research was a future prediction study using time series methods. The objective was to predict the proportion of elderly people with stress in Khon Kaen Province in fiscal year 2024. The population and sample were the elderly people screened for stress and found to have stress problems in Khon Kaen Province, fiscal year 2016 to 2024 (processed on April 20, 2024). The secondary data were collected from the Ministry of Public Health’s reporting system. The annual time series data were analyzed by developing models using polynomial regression methods and the Gray System Theory. The model with the highest accuracy was selected based on the coefficient determination and the mean absolute percentage error (MAPE). The results showed that the proportion of elderly people who undergo stress screening and were found to have stress problems in the fiscal years of the studied period fluctuated with an unclear increasing or decreasing trend. It was inappropriate to use a linear regression model. Therefore, the model developed according to the polynomial regression model and the Gray System Theory were used. The models developed using the polynomial regression equation of degree 4 and the GM (1,1) Error Periodic Correction (GM (1,1) EPC) had a coefficient of determination of 78 and 80, respectively, with highly consistent predicted values with actual values; MAPEs were 40.65 and 39.44, respectively, within the criteria for appropriate forecasting. Therefore, the forecast value for the proportion of elderly people with stress in fiscal year 2024 should be between the forecast value of the GM (1,1) EPC model and the model using the polynomial regression method, which is 4.72 to 10.40 percent, while the actual value in fiscal year 2024 (processed data on April 20, 2024) was 7.45 percent.
References
Center of Reinforcement for Research, Mahidol University. (2024). Self-assessment form whether an activity is human subject research which requires ethical approval (Eng, Thai). Retrieved from https://bit.ly/3UJRA1Y (in Thai)
Cheng, T., Bai, Y., Sun, X., Ji, Y., Zhang, H., & Li, X. (2022). Epidemiological analysis of varicella in Dalian from 2009 to 2019 and application of three kinds of model in prediction prevalence of varicella. BMC Public Health, 22(678), 1-9. https://doi.org/10.1186/s12889-022-12898-3
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice (2nd ed.). Retrieved from https://otexts.com/fpp2/
Khaweewong, D., & Duangsong, R. (2020). Factors related with stress of elderly people in Khon Kaen Municipality. KKU Journal for Public Health Research, 3(2), 36-46. (in Thai)
Lewis, C. D. (2023). Industrial and business forecasting methods. London: Butterworths.
Lin, Y. H, Chiu, C. C., Lin, Y. J., & Lee, P. C. (2013). Rainfall prediction using innovative grey model with the dynamic index. Journal of Marine Science and Technology, 21(1), 63-75. https://jmstt.ntou.edu.tw/cgi/viewcontent.cgi?article=1677&context=journal
Liu, S., & Lin, Y. (2010). Grey systems theory and application. Verlag: Springer.
Longstreet, D. (2015). Polynomial models explained (for the non-data scientist). Retrieved from https://bit.ly/4fhHg9R
Ministry of Public Health. (2024). Standard reporting group, promote and prevent mental health problems, stress screening (ST-5) in the elderly group. Retrieved from https://bit.ly/40MPD8C (in Thai)
Pennstate Eberly College of Science. (2018a). STAT 462 applied regression analysis, 7.7-polynomial regression. Retrieved from https://online.stat.psu.edu/stat462/node/158/
Pennstate Eberly College of Science. (2018b). STAT 200 elementary statistics, 3.4.2-correlation. Retrieved from https://online.stat.psu.edu/stat200/lesson/3/3.4/3.4.2
Seangpraw, K., Auttama, N., Kumar, R., Somrongthong, R., Tonchoy, P., & Panta, P. (2020). Stress and associated risk factors among the elderly: A cross-sectional study from rural area of Thailand. F1000Research, 8(655), 1-14. https://doi.org/10.12688/f1000research.17903.2
Suwannacheep, S., Rattanakorn, N., Wanichrammanee, K., Panuwattsuk, P., & Prasanthong, N. (2015). Guidelines for psychosocial care of the elderly to prevent mental health problems (4th ed.). Bangkok: Agricultural Cooperatives Association of Thailand Limited. (in Thai)
Tomov, L., Chervenkov, L., Miteva, D. G., Batselova, H., & Velikova, T. (2023). Applications of time series analysis in epidemiology: Literature review and our experience during COVID-19 pandemic. World Journal of Clinical Cases, 11(29), 6974–6983. https://doi.org/10.12998/wjcc.v11.i29.6974
Wilson, D. (2024). The most and least stressed countries in the world. Retrieved from https://ceoworld.biz/2024/03/26/the-most-and-least-stressed-countries-in-the-world-2024/
World Health Organization. (2023). Stress. Retrieved from https://bit.ly/4fGwoSt
Yang, X., Zou, J., Kong, D., & Jiang, G. (2018). The analysis of GM (1,1) grey model to predict the incidence trend of typhoid and paratyphoid fevers in Wuhan City, China. Medicine, 97(34), e11787. https://doi.org/10.1097/MD.0000000000011787
Zhao, D., Zhang, H., Cao, Q., Wang, Z., He, S., Zhou, M., & Zhang, R. (2022). The research of ARIMA, GM (1,1), and LSTM models for prediction of TB cases in China. PloS One, 17(2), e0262734. https://doi.org/10.1371/journal.pone.0262734
