Development of a Robust Statistical Approach for Selecting Economic Variables Affecting Economic Growth: An Applied Study of the Iraqi Economy
Ключевые слова:
Robust Regression, Variable Selection, Huber Loss Function, Adaptive Elastic Net, Iraqi EconomyАннотация
This study aims to develop a robust statistical approach for selecting economic variables affecting economic growth by integrating the Huber loss function, Adaptive Elastic Net regularization, and stability selection. The proposed approach seeks to improve variable selection accuracy and estimation reliability in the presence of outliers, multicollinearity, and data instability. Its performance was evaluated through Monte Carlo simulation involving 500 replications under four different scenarios, and compared with OLS, LASSO, Elastic Net, Adaptive LASSO, and Huber-AEN methods.
Furthermore, the proposed methodology was applied to the Iraqi economy using annual macroeconomic data obtained from the World Bank for the period 2000–2021. GDP growth was considered the dependent variable, while inflation, foreign direct investment, oil rents, and population growth were included as explanatory variables. The empirical results showed that all four explanatory variables exceeded the predefined stability selection threshold. The simulation findings also indicated that robust estimation techniques reduced coefficient estimation errors under different contamination conditions, although the proposed method did not outperform all competing methods in every scenario.
The study concludes that combining robust estimation, adaptive regularization, and stability selection provides a useful statistical framework for identifying economic variables affecting growth, particularly when dealing with contaminated observations and correlated predictors.
Библиографические ссылки
Bergmeir, C., Hyndman, R. J., & Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120, 70–83.
Huber, P. J. (1964). Robust estimation of a location parameter. The Annals of Mathematical Statistics, 35(1), 73–101.
Kepplinger, D. (2023). Robust variable selection and estimation via adaptive elastic net S-estimators for linear regression. Computational Statistics & Data Analysis, 183, 107730.
Kock, A. B., Medeiros, M., & Vasconcelos, G. (2020). Penalized time series regression. In P. Fuleky (Ed.), Macroeconomic forecasting in the era of big data (pp. 193–228). Springer.
Künsch, H. R. (1989). The jackknife and the bootstrap for general stationary observations. The Annals of Statistics, 17(3), 1217–1241.
Lambert-Lacroix, S., & Zwald, L. (2011). Robust regression through the Huber’s criterion and adaptive lasso penalty. Electronic Journal of Statistics, 5, 1015–1053.
Meinshausen, N., & Bühlmann, P. (2010). Stability selection. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 72(4), 417–473.
Wisnowski, J. W., Simpson, J. R., Montgomery, D. C., & Runger, G. C. (2003). Resampling methods for variable selection in robust regression. Computational Statistics & Data Analysis, 43(3), 341–355.
World Bank. (n.d.-a). Foreign direct investment, net inflows (% of GDP) – Iraq. World Development Indicators.
World Bank. (n.d.-b). GDP growth (annual %) – Iraq. World Development Indicators.
World Bank. (n.d.-c). Inflation, consumer prices (annual %) – Iraq. World Development Indicators.
World Bank. (n.d.-d). Oil rents (% of GDP) – Iraq. World Development Indicators.
World Bank. (n.d.-e). Population growth (annual %) – Iraq. World Development Indicators.
Zou, H. (2006). The adaptive lasso and its oracle properties. Journal of the American Statistical Association, 101(476), 1418–1429.
Загрузки
Опубликован
Как цитировать
Выпуск
Раздел
Лицензия

Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.





