Using Box – Jenkins Methodology to Forecasting GDP in Libya (2024-2030)

Abstract

This study analyzed the behavior of the time series of the real GDP variable in Libya by employing the Box-Jenkins methodology, which is one of the modern models that has the ability to accurately predict and determine the trends of macroeconomic indicators in comparison to the previous values and optimal lag periods for these variables. The study used time series data obtained from the World Bank database for the period 1980-2023. In order to predict future values for the period (2024-2030), stationarity tests were conducted according to the Augmented Dickey-Fuller test and the Phillips-Perron test. The results showed that the time series is stationary at the level and order of integration I (0).  Steps of the Box-Jenkins methodology was applied, which is represented in the identification and estimation stages, in addition to the diagnostic and forecasting stage. The estimation  results showed that the optimal model for forecasting is  ARMA(2,1), while the diagnosis results indicated that the estimated model is free of the problem of autocorrelation and serial correlation, in addition to that the residuals was stable and that it follows the Normal Distribution and homogeneous variance, indicating that the estimated model is free of Standard problems. Finally, the results of the forecasting of the future values of the real GDP variable in Libya during the period (2024-2030) indicated that the estimated GDP values   are very close to the actual values. The expected values of the variable during the forecasting period were increasing and fluctuating between the beginning and end of the forecasting period, indicating that developments in GDP in Libya are largely linked to external factors related to global markets.