Munich Personal RePEc Archive

Modeling and Forecasting Naira / USD Exchange Rate In Nigeria: a Box - Jenkins ARIMA approach

Nyoni, Thabani (2018): Modeling and Forecasting Naira / USD Exchange Rate In Nigeria: a Box - Jenkins ARIMA approach.

[img]
Preview
PDF
MPRA_paper_88622.pdf

Download (564kB) | Preview

Abstract

In the financial as well as managerial decision making process, forecasting is a crucial element (Majhi et al, 2009). Most research have been made on forecasting of financial and economic variables through the help of researchers in the last decades using series of fundamental and technical approaches yielding different results (Musa et al, 2014). The theory of forecasting exchange rate has been in existence for many centuries where different models yield different forecasting results either in the sample or out of sample (Onasanya & Adeniji, 2013). A country’s exchange rate is one of the most closely monitored indicators, as fluctuations in exchange rates can have far reaching economic consequences (Ribeiro, 2016). The recent financial turmoil all over the world demonstrates the urgency of perfect information of the exchange rates (Shim, 2000). Understanding the forecasting of exchange rate behaviour is important to monetary policy (Simwaka, 2007). One of the important variables that have considerable influence on other socio – economic variables in Nigeria is the Nigerian naira / dollar exchange rate (Ismail, 2009). Owing to the critical role played by exchange rate dynamics in international trade and overall economic performance of all countries in general, the need for a good forecasting tool cannot be ruled out. In this study, we model and forecast the Naira / USD exchange rates over the period 1960 – 2017. Our diagnostic tests such as the ADF test indicate that EXC time series data is I (1). Based on the minimum AIC value, the study presents the ARIMA (1, 1, 1) model as the optimal model. The ADF test further indicates that the residuals of the ARIMA (1, 1, 1) model are stationary and thus bear the characteristics of a white noise process. It is also important to note that our forecast evaluation statistics, namely ME, RMSE, MAE, MPE, MAPE and Theil’s U absolutely show that our forecast accuracy is quite good. Our forecast actually indicates that the Naira will continue to depreciate. The main policy implication from this study is that the Central Bank of Nigeria (CBN), should devalue the Naira in order to not only restore exchange rate stability but also encourage local manufacturing and promote foreign capital inflows.

UB_LMU-Logo
MPRA is a RePEc service hosted by
the Munich University Library in Germany.