Research Article

A SARIMA and Adjusted SARIMA Models in a Seasonal Nonstationary Time Series; Evidence of Enugu Monthly Rainfall

Chibuzo Gabriel Amaefula
Federal University Otuoke, Nigeria
* Corresponding author
DOI icon 10.24018/ejmath.2021.2.1.15

Read Counter
508

Downloads
540

Citations

Share

Article Sidebar

Submitted 2021-01-31
Published 2021-02-19

Read counter = 508 times

Table of Contents

Article Main Content

 The paper compares SARIMA and adjusted SARIMA(ASARIMA) in a regular stationary series where the underlying variable is seasonally nonstationary.  Adopting empirical rainfall data and Box-Jenkins iterative algorithm that calculates least squares estimates, Out of 11 sub-classes of SARIMA and 7 sub-classes of ASARIMA models, AIC chose ASARIMA(2,1,1)12 over all sub-classes of SARIMA(p,0,q)x(P,1,Q)12 identified. Diagnostic test indicates absence of autocorrelation up to the 48th lag. The forecast values generated by the fitted model are closely related to the actual values. Hence, ASARIMA can be recommended for regular stationary time series with seasonal characteristics and where parameter redundancy and large sum of square errors are penalized.

       

Keywords: AIC ASARIMA model rainfall seasonal nonstationary time series

References

  1. Afrifa-Yamoah E , I. I. Bashiru Saeed , A. Karim ( 2016) Sarima Modelling and Forecasting of Monthly Rainfall in the Brong Ahafo Region of Ghana, World Environment, Vol. 6 No. 1, 2, pp. 1-9.
     Google Scholar
  2. Akpanta A. C, I. E. Okorie1 and N. N. Okoye (2015). SARIMA
     Google Scholar
  3. Modelling of the Frequency of Monthly Rainfall in Umuahia, Abia State of Nigeria. American Journal of Mathematics and Statistics; 5(2): 82-88.
     Google Scholar
  4. Alawaye A.I and A.N.Alao(2017). Time Series Analysis on Rainfall in Oshogbo Osun State, Nigeria, International Journal of Engineering and Applied Sciences (IJEAS); 4(7): Pp.35-37.
     Google Scholar
  5. Amaefula, C. G..(2011). Optimal identification of subclass of
     Google Scholar
  6. autoregressive integrated moving average model using sum of square deviation forecasts criterion. International Journal of Statistics and System.2011; 6(1): Pp.35-40.
     Google Scholar
  7. Amaefula, C. G.,(2018). Modelling Mean Annual Rainfall Pattern in Port Harcourt, Nigeria. EPRA International Journal of Research and Development (IJRD); 3(8): Pp.25-32.
     Google Scholar
  8. Amaefula, C. G.,(2019). Modelling Monthly Rainfall in Owerri, Imo State Nigeria using SARIMA. EPRA International Journal of Multidisciplinary Research (IJMR); 5(11): Pp.197 – 206.
     Google Scholar
  9. Box G.E.P and G.M.Jenkins(1976). Time Series Analysis, Forecasting and Control, Holden-Day: San Francisco.
     Google Scholar
  10. Box, G. E. P. and G. M.Jenkins, (1994). “Time Series Analysis, Forecasting and Control”, 3rd Edition. Prentice Hall, ,1994
     Google Scholar
  11. Dickey, D.A. and W.A.,Fuller (1979).“Distribution of the Estimators for Autoregressive Time Series with a u nit root,” Journal of the American Statistical Association; 74: Pp.427–431.
     Google Scholar
  12. Edwin A. and O.Martins(2014) Stochastic Characteristics and Modelling of Monthly Rainfall Time Series of Ilorin, Nigeria: Open Journal of Modern Hydrology; Vol. 4: Pp.67-69.
     Google Scholar
  13. Elliott, G., T.J. Rothenbergand J.H. Stock(1996). Efficient test for an autoregressive unit root. Econometrica; 64(4): Pp.813-336.
     Google Scholar
  14. Etuk H. E, U. I. Moffat and E. B.Chims (2013). Modelling Monthly Rainfall Data of Port Harcourt, Nigeria by Seasonal Box-Jenkins Methods, International Journal of Sciences.; 2(7):Pp 60-67.
     Google Scholar
  15. Igwenagu, C. M.,(2015).Trend Analysis of Rainfall Pattern in Enugu State Nigeria. European Journal of Statistics and Probability; 3(3): Pp.12-18.
     Google Scholar
  16. Nirmala, M and S.M.Sundaram,(2010). A Seasonal ARIMA Model for Forecasting monthly rainfall in Tamilnadu. National Journal on Advances in Building Sciences and Mechanics. 1(2): Pp. 43-47.
     Google Scholar
  17. Osarumwense, O.I.,(2013). Applicability of Box Jenkins SARIMA Model in Rainfall Forecasting: A Case Study of Port-Harcourt South-South Nigeria. Canadian Journal on Computing in Mathematics, Natural Sciences, Engineering and Medicine. 4(1) :Pp.1-5.
     Google Scholar
  18. Yusuf, F andI. L Kane (2012). Modeling Monthly Rainfall Time Series using ETS state space and SARIMA models. International Journal of Current Research.2012; 4(9): Pp. 195 – 200.
     Google Scholar