Sanae Saber

As part of my Master's thesis in Applied Economics and Modeling, I conducted in-depth research on the impact of foreign direct investment (FDI) on economic growth in Morocco, using annual data spanning an exceptionally long period from 1960 to 2024, covering over six decades of macroeconomic evolution.

The main objective of this study was to determine if a long-term relationship (cointegration) exists between FDI flows and Moroccan GDP growth, while distinguishing between short-term effects and long-term structural effects. To address this issue, I used the Autoregressive Distributed Lag (ARDL) model, an econometric approach particularly suitable when variables exhibit mixed orders of integration (I(0) and I(1)).

My methodology involved several rigorous steps: unit root tests to verify the stationarity of the series, selection of the optimal ARDL model using information criteria (AIC), and then application of the Bounds Test to confirm the existence of a cointegration relationship between the variables. The final selected model, ARDL(1,0,2,0,1,0), produced an F-statistic of 22.869, significantly higher than the upper critical values, confirming a strong and robust cointegration between FDI and economic growth.

I also estimated the Error Correction Coefficient (CointEq), which was -1.4448, a result indicating a rapid adjustment speed towards long-term equilibrium after an economic shock. Beyond statistical tests, I performed comprehensive model validation diagnostics, including Variance Inflation Factor (VIF) tests to rule out any multicollinearity issues between explanatory variables, as well as coefficient stability tests.

Independent freelancer specializing in data analysis and machine learning applied to finance. I have delivered 5 end-to-end projects: banking fraud detection (ROC-AUC 0.981), credit risk scoring, customer churn prediction, e-commerce business intelligence (2.4M MAD analyzed), and sales forecasting (SARIMA/Prophet). Technical stack: Python, SQL, Power BI, XGBoost, SHAP.