Comparison between Efficiency of Poisson Regression Model and Negative Binomial Regression in the Analysis of Factors Affecting Mortality from Cardiovascular Diseases in Yazd Province in 2017
Mohammad Mirjani Arjenan(MS.c)1, Mohsen Askarshahi(Ph.D.)2, Mahmud Vakili(Ph.D.)3
1.M.Sc. Student in Biological Statistics, International Campus, Shahid Sadoughi University, Yazd, Iran
Graduate student of Biostatistics, Shahid Sadoughi University of Medical Sciences, Yazd
2. Corresponding Author :Associate Professor, Department of Statistics and Epidemiology, Faculty of Health., Shahid Sadoughi University of Medical Sciences, Yazd, Iran. E-mail:
moasbio@gmail.com Tel:09125799189
3.MD, MPH, Associate Professor in Community Medicine, Health Monitoring Research Center, School of Medicine, Shahid Sadoughi University of Medical Sciences, Yazd, Iran.
Abstract
Introduction: Despite the advances in cardiovascular diseases, death caused by these diseases is still considered as the leading cause of mortality. In this study, some of the effective factors on the deaths caused by cardiovascular diseases were investigated
Methods: This cross-sectional analytical study investigated the efficacy of Poisson regression models and negative binomial regression models on factors affecting mortality from cardiovascular diseases
. The death data were extracted from the death registration system for Yazd province in 2017
.Gender, age, education, occupation, location, and city of death were also extracted for each deceased. The two regression models were then fitted to the data
Results: A total of 5,015 deaths were recorded, of which 1,642 were due to cardiovascular diseases
.
Cardiovascular disease mortality rates were significant using negative binomial regression in terms of the educational variables, place of residence, type of residence, and age. Death rates caused by cardiovascular diseases were not significant for age and occupational, educational, and residential variables.
Conclusion: If the time of death is considered as an offset variable, the regression model of two negative sentences is more effective in showing the factors affecting death due to cardiovascular diseases according to AIC and BIC criteria. In the case that the total number of deaths is considered as the offset variable, the Poisson regression model is more efficient
.
Keywords: Cardiovascular Disease, Negative Binomial Regression, Poisson Regression, Performance, Akaike Score, Bayesian Score
Conflict of interest: The authors declared that there is no conflict of interest.
1-Abubakar I, Tillmann T, Banerjee A. Global, regional, and national age-sex specific all-cause and cause-specific mortality for 240 causes of death, 1990-2013: a systematic analysis for the Global Burden of Disease Study 2013. Lancet. 2015;385(9963):117
-71
.
2-Kazemnejad A, Faramand S, Zayeri F, Salehi M, Yazdani Cherati J. Preparing the geographical maps of the relative death rate out of vasco-cardiac diseases in cities of the mazandaran province in 2008. Journal of Mazandaran University of Medical Sciences.2012;22(94):63-9
.
3-Forouzanfar MH, Sepanlou SG, Shahraz S, BESc PN, Pourmalek F, Lozano R, et al. Evaluating causes of death and morbidity in Iran, global burden of diseases, injuries, and risk factors study 2010. Archives of Iranian medicine. 2010; 304:(5)17;14
.
4-Kontis V, Mathers CD, Bonita R, Stevens GA, Rehm J, Shield KD, et al. Regional contributions of six preventable risk factors to achieving the 25× 25 non-communicable disease mortality reduction target: a modelling study. The Lancet Global Health. 2015;3(12):e746-e57
.
5-Rashidi M, Ghias M, Ramesht MH. Geographical Epidemiology of Death Due to Cardiovascular Diseases in Isfahan Povince, Iran. Journal of Isfahan Medical School. 2011;29(125)
.
6-Rezaeian M, Dehdarinejad A, Esmaili Nadimi A
, Tabatabaie S. Geographical epidemiology of deaths due to cardiovascular diseases in counties of kerman province. Iranian Journal of Epidemiology. 2008;4(1):35-41
.
7-Woodward M. Cardiovascular disease and the female disadvantage. International journal of environmental research and public health. 2019;16(7):1165
.
8-Mertler CA, Reinhart RV. Advanced and multivariate statistical methods: Practical application and interpretation: Routledge; 2016
.
9-Kulkarni VG. Modeling and analysis of stochastic systems: Chapman and Hall/CRC; 2016
.
10-Imprialou M-IM, Quddus M, Pitfield DE, Lord D. Re-visiting crash–speed relationships: A new perspective in crash modelling. Accident Analysis & Prevention. 2016;86:173-85
.
11-Coggins BL. Comparing models for fitting count data: University of South Carolina; 2009
.
12-Chow N, Steenhard D. A flexible count data regression model using SAS Proc nlmixed. SAS Global Forum: Statistics and Data Analysis; 2009: Citeseer
.
13-Cox DR. Analysis of binary data: Routledge; 2018
.
14-Ardiles LG, Tadano YS, Costa S, Urbina V, Capucim MN, da Silva I, et al. Negative Binomial regression model for analysis of the relationship between hospitalization and air pollution. Atmospheric Pollution Research.2018;9(2):333-41
.
15-Waenerlund AK, Mosquera PA, Gustafsson PE, San Sebastian M. Trends in educational and income inequalities in cardiovascular morbidity in middle age in Northern Sweden 1993–2010. Scandinavian journal of public health. 2018:1403494818790406
.
16-Correia JC, Braillard O, Combescure C, Gerstel E, Spechbach H. Admission rates in emergency departments in Geneva during tennis broadcasting: a retrospective study. BMC emergency medicine. 2018;18(1):56
.
17-Joe H, Zhu R. Generalized Poisson distribution: the property of mixture of Poisson and comparison with negative binomial distribution. Biometrical Journal: Journal of Mathematical Methods in Biosciences. 2005;47(2):219-29
.
18-Chang LY. Analysis of freeway accident frequencies: negative binomial regression versus artificial neural network. Safety science. 2005;43(8):541-57
.
19-Sharifirad G, Mohebbi S, Matlabi M. The relationship of physical activity in middle age and cardiovascular problems in old age in retired people in Isfahan, 2006. The Horizon of Medical Sciences
.2007;13(2):57-63.
20-Dogra S, Ardern CI, Baker J. The relationship between age of asthma onset and cardiovascular disease in Canadians. Journal of Asthma. 2007;44(10):849-54
.
21-Ameri H, Alizadeh S, Barzegari A. Identification of influencing factors for heart attack in diabetic patients using C & R algorithm. 2014
.
22-Finegold JA, Asaria P, Francis DP. Mortality from ischaemic heart disease by country, region, and age: statistics from World Health Organisation and United Nations. International journal of cardiology.2013;168(2):934-45
.
23-Furer A, Afek A, Orr O, Gershovitz L, Rabbi ML, Derazne E, et al. Sex-specific associations between adolescent categories of BMI with cardiovascular and non-cardiovascular mortality in midlife. Cardiovascular diabetology. 2018;17(1):80
.
24-Sun LY, Tu JV, Sherrard H, Rodger N, Coutinho T, Turek M, et al. Sex-Specific trends in incidence and mortality for urban and rural ambulatory patients with heart failure in eastern Ontario from 1994 to 2013. Journal of cardiac failure. 2018;24(9):568-74
.
25-Abdollahi AA, Hoseini SA, Salehi A, Behnampour N, Abasi A. Coronary artery lesions and some of its related factors in more than 5000 patients in kosar Angiography Center (Golestan Province) from 2007 to 2009. Scientific Journal of Kurdistan University of Medical Sciences. 2012;17(1):18-24
.
26-Darvishpour A, Javadi Pashaki N, Salari A, Taleshan Nejad M, Barari F. Comparing the quality of life in patients with cardiovascular diseases before and after coronary angioplasty. Journal of Mazandaran University of Medical Sciences. 2016;26(137):206-10
.
27-Asefzadeh S, Alikhani S, Javadi H. Socio-economic status and mortality from cardiovascular diseases in Qazvin (2009). 2013
.