THE COMPARISON BETWEEN ARTIFICIAL NEURAL NETWORKING AND BOX-JENKINS METHODOLOGY FOR FORECASTING OF MORTALITY RATE.
- Department of Statistics, University of Sargodha, Sargodha, Pakistan.
- Abstract
- Keywords
- References
- Cite This Article as
- Corresponding Author
It is impossible to ignore the demographic changes due to their impact on development of the country as well as effects on all areas of human activities. Forecasting demographic variables help us to control the situation in time. The demographic trends also support in policy making. Mortality rate is an important indicator to evaluate the provision of health facilities by the government. The techniques used for forecasting are also important in this regard. So, we are going to make comparison between two techniques (Box-Jenkins and Artificial Neural Networking (ANN)) which are extensively used for forecasting. For this purpose, we utilize the data related to mortality rate of Pakistan from 1975-2014. Two models (Autoregressive Integrated Moving Average (ARIMA) (15,2,1), and ARIMA (1,2,2)) are selected using Schwarz Criterion (SC) for Box-Jenkins methodology and compared with ANN based on Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results depict that ANN is more appropriate technique for forecasting as compare to Box-Jenkins.
- Adetunji, J. (2000). Trends in under-5 mortality rates and the HIV/AIDS epidemic. World Health Organization, 78(10), 1200-1206.
- Ali, A., Qamar, S., Zubair, M., Akhtar, N., and Iqbal, M. (2016). A Comparative Study Of Pakistan, Bangladesh And India On The Basis Of Mortality Rate Under Five Years. Journal of ISOSS, 2(1), 79-84.
- Black, R.E., Morris, S.S. and Bryce, J. (2003). Where and why are 10 million children dying every year? The Lancet, 361, 2226-2234.
- Garenne, M., Ronsmans, C. and Campbell, H. (1992). The Magnitude of mortality from acute respiratory infections in childern under 5 years in developing countries. World Health Statistics Quarterly, 45, 180-191.
- Kipp, A.M., Blevins, M., Haley, C.A., Mwinga, K., Habimana, P., Shepherd, B.E., Aliyu, M.H., Ketsela, T. and Vermund, S.H. (2016). Factors associated with declining under-five mortality rates from 2000 to 2013: an ecological analysis of 46 African countries. BMJ Open, 6, 1-11.
- Rajaratnam, J.K., Marcus, J.R., Haxman, A.D., Wang, H., Rector, A.L., Costa, M., Lopez, A.D. and Murray, C.J.L. (2010). Neonatal, postneonatal, childood, and under-5 mortality for 187 countries, 1970-2010: a systematic analysis of progress towards Millennium Development Goal 4. The Lancet, 375, 1988-2008.
- Wang, Y., Li, X., Zhou, M., Luo, S., Liang, J., Liddell, C.A., Coates, M.M., Gao, Y., Wang, L., He, C., Kang, C., Liu, S., Dai, L., Schumacher, A.E., Fraser, M.S., Wolock, T.M., Pain, A., Levitz, C.E., Singh, L., Coggeshall, M., Lind, M., Li, Y., Li, Q., Deng, K., Mu, Y., Deng, C., Yi, L., Liu, Z., Ma, X., Li, H., Mu, D., Zhut, J., Murrayt, C.J.L. and Wang, H. (2015). Under-5 mortality in 2851 Chinese countries, 1996-2012: a subnational assessment of achieving MDG 4 goals in China. The Lancet, 1-11.
- Zakir, M. and Wunnava, P. V. ( 1999). Factors affecting infant mortality rates: evidence from cross-sectional data. Applied Economics Letters, 6, 271?273.
[Asad Ali and Muhammad Zubair. (2017); THE COMPARISON BETWEEN ARTIFICIAL NEURAL NETWORKING AND BOX-JENKINS METHODOLOGY FOR FORECASTING OF MORTALITY RATE. Int. J. of Adv. Res. 5 (May). 1090-1095] (ISSN 2320-5407). www.journalijar.com
Department of Statistics, University of Sargodha
