CBN Journal of Applied Statistics (JAS)


External Reserves, ARIMA, SARIMA, SARIMA-X, ARDL, Statistical Loss Functions


This paper proposes three short-term forecasting models for the adjusted external reserves using the seasonal autoregressive integrated moving average (SARIMA), seasonal autoregressive integrated moving average with an exogenous input (SARIMA-X) and an autoregressive distributed lag (ARDL) processes. The performances of the proposed models are compared with the existing model obtained using an autoregressive integrated moving average (ARIMA) process using the pseudo-out-of-sample forecasting procedure over July 2013 to May 2014. The results show that SARIMA model outperformed the other models in three to six months forecast horizon, whereas ARDL model performs better in one to two months forecast horizon. Therefore, in forecasting external reserves in longer horizon, the paper concludes that seasonality should be accounted for by using the SARIMA model.

Author Bio

The authors are staff of the Economic Policy Directorate, Central Bank of Nigeria, Abuja – Nigeria. The views expressed in the paper are those of the authors and do not necessarily represent the views of the Central Bank of Nigeria. The authors acknowledge the pertinent comments of the referees which have led to tremendous improvements on the earlier version of the paper. They are also grateful to O.N. Edem for the provided research assistance.

Publication Title

CBN Journal of Applied Statistics







To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.