Forecasting time series using Vector Autoregressive Model

Document Type : Research Paper


College of Arts - Information Technology Unit, University of Baghdad, Baghdad, Iraq.


In this study, a vector Autoregressive model was used to analysis the relationship between two time series as well as forecasting. Two financial time series have been used, which are a series of global monthly oil price and global monthly gold price in dollars for a period from January 2015 to Jun 2019. It has 54 monthly values, where the data has been transferred to get the Stationarity, Diekey Fuller test for the Stationarity was conducted. The best three order for model was determined through a standard Akaike information AIC, it is VAR(7) , VAR(8) and VAR(10) respectively. The comparison was made between selected orders by AIC based on the accuracy measure and mean square error (MSE). It turns out that less MSE value of the VAR(10) model. Some tests were conducted like Lagrange-multiplier, Portmanteau, Jarque - Bera to residuals for the selected model, with forecasting for the VAR(10) model for the period from Jun 2019 to Jun 2021 , It is 24 monthly value. It turns out that less MSE for forecasting value for oil price series is to VAR(7) model and less MSE for forecasting value for gold price series is VAR(10) model. The results have been computed through the Stata program.


[1] K. Bulteel, Multivariate time series vector autoregressive models and dynamic networks in psychology Extensions and reflections, Faculty of Psychology and Educational Sciences, Doctoral Thesis, 2018.
[2] S. Hartini, M.P. Hadi, S. Sudibyakto and A. Poniman, Application of vector autoregression model for rainfall-river discharge analysis, Forum Geog. 29(1) (2015) 1–10.
[3] C.Y. Keng, F.P. Shan, K. Shimizu, T. Imoto, H. Lateh and K.S. Peng, Application of vector autoregressive model for rainfall and groundwater level analysis, AIP Conf. Proc. 1870(1) (2017) 060013-1–060013-8.
[4] T.M. Khaleel and E.A.E. Shehata, An econometric study of dynamic models with application on forecasting labor in Egypt, Egyptian Statistical Society, The 29th Int. Conf. Stat. Computer Sci. Appl. (2004) 133–154.
[5] H. Luetkepohi, Vector Autoregressive Models, European University Institute, Florence, 2011.
[6] F.X. Mohr, An Introduction to Vector Autoregression (VAR), R-Econometrics, 2018.
[7] S. Safawi and M. Yahya, Analysis the relationship between world prices of Oil, Euro and Gold using vector autoregressive (VAR), Iraqi J. Stat. Sci. 8(14) (2008) 15–42.
[8] Stata Corp., STATA base reference manual Release 13, Stata Corp. Statistical Software., College Station, TX: Stata. Corp. LP., 2013.
[9] Warsono, E. Russels, Wamiliana, Widiarti and M. Usman, Vector autoregressive with exogenous variable model and its application in modeling and forecasting energy data: Case study of PTBA and HRUM energy, Int. J. Energy Econ Policy 9(2) (2019) 390–398.
[10] E. Zivot and J. Wang, Modeling Financial Time Series with S-PLUS, Springer Science and Business Media, 2006.
Volume 13, Issue 1
March 2022
Pages 499-511
  • Receive Date: 04 March 2021
  • Revise Date: 17 April 2021
  • Accept Date: 20 May 2021