Foreign Direct Investment and Economic Growth in Nepal: Evidence from ARDL and ARIMA Forecasting Models

Abstract

This study investigates the relationship between foreign direct investment (FDI) and economic growth in Nepal using annual time-series data from 1990 to 2024. Employing the Autoregressive Distributed Lag (ARDL) bounds testing approach, the analysis examines both short-run dynamics and long-run equilibrium relationships between GDP growth and FDI. The empirical results reveal that FDI does not exert a statistically significant effect on economic growth in the short run. However, the bounds test confirms the existence of a stable long-run cointegrating relationship between FDI and GDP growth. The estimated error correction model indicates rapid adjustment toward long-run equilibrium, suggesting that deviations caused by short-term shocks are corrected swiftly, albeit with evidence of overshooting behavior. Structural break analysis further identifies regime changes in Nepal’s growth trajectory. To assess predictive performance, the forecasting accuracy of the ARDL model is compared with that of an ARIMA framework using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results indicate that the ARDL model provides marginally superior forecasting accuracy relative to the ARIMA model. Overall, the findings suggest that while FDI does not stimulate immediate economic growth in Nepal, its long-run contribution depends critically on domestic absorptive capacity, institutional quality, and policy stability.