Multivariate Multilevel Modelling of Diarrheal Disease Data in Low-and Middle-Income Countries
[1]
J. A. Chanika Jayangani Perera, Department of Statistics, University of Colombo, Colombo, Sri Lanka.
[2]
M. R. Sooriyarachchi, Department of Statistics, University of Colombo, Colombo, Sri Lanka.
Past literature has shown that the key factors influencing diarrheal deaths are unsafe water, unsafe sanitation and unsafe hygiene. In the year 2000 there were estimated to be 1.73 million deaths worldwide due to diarrhea. Therefore, this is a major health issue, particularly in low and middle income countries. The objective of this research was therefore to investigate the factors associated with unsafe water deaths (UWD), unsafe sanitation deaths (USD) and unsafe hygiene deaths (UHD) with respect to diarrhea. The data set consists of the estimates of global burden of diarrheal disease from inadequate water, sanitation and hygiene for 145 low and middle income countries (LMICs) for the year 2012. Since these countries are nested within regions geographically, multilevel analysis and modeling have been considered. Initially, in the preliminary ananlysis, a graphical analysis, which is based on bar charts and mosaic plots was carried out on the data of interest. It was then followed by Generalized CochranMantel Haenszel (GCMH) test in order to obtain more insight into the relationships as an univariate analysis. The results of univariate phase, which almost tallied with the results of the graphical analysis showed that there are some significant factors for three types of diarrheal deaths. The preliminary analysis was further followed by an advanced analysis, which adopted univariate multilevel linear regression models acting as an initialization to the multivariate stage as well as multivariate multilevel linear regression model. Moreover, most of results obtained from the univariate phase were further established in the advanced modeling phase. The modeling phase showed significant region level variations showing it is necessary to consider the multilevel concept in this study. The results in the modeling phase showed that Africa contributed to a higher risk of UWD, USD and UHD and Europe contributed to a lower risk of UWD, USD and UHD.
Diarrhea, Unsafe Water Deaths (UWD), Unsafe Sanitation Deaths (USD), Unsafe Hygiene Deaths (UHD), Multilevel Modeling
[1]
World Health Organization. (2013). Retrieved from WHO|Diarrhoeal disease: http://www.who.int/mediacentre/factsheets/fs330/en/
[2]
Ashish Joshi and Chioma Amadi, “Impact of Water, Sanitation, and Hygiene Interventions on Improving Health Outcomes among School Children,” Journal of Environmental and Public Health, vol. 2013, Article ID 984626, 10 pages, 2013. https://doi.org/10.1155/2013/984626.
[3]
Taylor DL, Kahawita TM, Caircross S, Ensink JHJ. (2015). The Impact of Water, Sanitation and Hygiene Interventions to Control Cholera: A systematic review. PLoS ONE, 10 (8).
[4]
Ezeh OK, Agho KE, Dibley MJ, Hall J et al. (2014). The impact of water and sanitation on childhood mortality in Nigeria: evidence from demographic and health surveys, 2003-2013. Int J Environ Res Public Health. 2014 Sep 5; 11 (9): 9256-72. doi: 10.3390/ijerph110909256.
[5]
Elizabeth Omoladun Oloruntoba, Taiwo Bukola Folarin, Adejumoke Idowu Ayede (2014). Hygiene and sanitation risk factors of diarrhoeal disease among under-five children in Ibadan, Nigeria. Afr Health Sci. 2014 Dec; 14 (4): 1001–1011. doi: 10.4314/ahs.v14i4.32
[6]
Assefa M, Kumie A. Assessment of factors influencing hygiene behaviour among school children in Mereb-Leke District, Northern Ethiopia: a cross-sectional study. BMC Public Health. 2014 Sep 26; 14: 1000. doi: 10.1186/1471-2458-14-1000.
[7]
Annette Prüss-Üstün et al. (2008). Safer Water, Better Health – Costs, Benefits and Sustainability to promote better health. Published by World Health Organization.
[8]
Subramanian, S., Kim, D., & Kawachi, I. (2005). BMJCovariation in the Socioeconomic DEterminants of Self Rated Health and Happiness: A Multivariate Multilevel Analysis of Individuals and Communities in the USA. Journal of Epidemiology and Community Health, 59 (8), 664-669.
[9]
Goldstein, H., & Kounali, D. (2009). Multilevel Multivariate Modelling of Childhood Growth, Numbers of Growth Measurements and Adult Characteristics. Journal of the Royal Statistical Society, 172 (3), 559-613.
[10]
Frank, R., Cerda, M., & Rendon, M. (2007). Barrios and Burds: Residential Contex Health-Risk Behaviour among Angeleno Adolescents. Journal of HEalth and Social Behavior, 48 (3), 283-300.
[11]
“PREVENTING DIARRHOEA THROUGH BETTER WATER, SANITATION AND HYGIENE” (201). Published by the World Health Organization (WHO).
[12]
De Silva, D., & Sooriyarachchi, M. (2012). Generalized Cochran Mantel Haenszel test for multilevel correlated categorical data: an algorithm and R function. J. Natn. Sci. Foundation Sri Lanka, 40 (2), 137-148.
[13]
Population Reference Bureau. (2012, July). Retrieved from PRB 2012 World Population Data Sheet: http://www.prb.org/pdf12/2012-population-data-sheet_eng.pdf
[14]
Gelman A & Park DK (2008) Splitting a predictor at the upper quarter or third and the lower quarter or third. The American Statistician 63, 1-8.
[15]
Goldstein, H. (1999). Multilevel Statistical Models.
[16]
Rasbash, J., Steele, F., Browne, W. J., & Goldstein, H. (2009). A User's Guide to MLwiN, version 2.10. Centre for Multilevel Modeling, University of Bristol.
[17]
K. N. O. Ranathunga, M. R. Sooriyarachchi. (2017). Multivariate Multilevel Modeling of Age Related Diseases. Journal of Morden Applied Statistical Models, 498-517.
[18]
Zhang J & Boos DD (1997) Generalized Cochran-Mantel-Haenszel Test Statistics for Correlated Categorical Data. Communications in Statistics 26, 1813-1837.
