Phương pháp ước lượng LASSO: Cơ sở toán học và ứng dụng

Authors

  • Mỹ Bùi Thị Thiện Trường Đại học Ngân hàng TP. Hồ Chí Minh Author

DOI:

https://doi.org/10.24311/jabes/2020.31.04.4

Keywords:

Regression, LASSO, Shrinkage model

Abstract

This paper introduces the LASSO estimation method for regression analysis. Similarly OLS estimation method, LASSO finds estimates of the parameters of a regression model by minimizing the objective function as the sum of squared-residuals. However, LASSO imposes a constraint on the sum of absolute values of parameters in the model by a tuning parameter. The paper presents an overview of the meaning and the mathematical background of LASSO. Besides, the paper introduces an empirical case applying LASSO estimation method to identify intrinsic factors affecting the ROA and ROE of Vietnamese joint stock commercial banks. The results show that LASSO has eliminated factors that do not affect ROA and ROE, providing a simpler regression model with a smaller MSE than OLS method does, although this improvement is not significant

References

Bertsekas, D. P., Nedic, A., & Ozdaglar, A. E. (2003). Convex Analysis and Optimization. Belmont, MA: Athena Scientific.

Boyd, S., & Vandenberghe, L. (2004). Convex Optimization. Cambridge, UK: Cambridge

University Press.

Casella, G., & Berger, R. (2002). Statistical Inference (2nd ed.). Pacific Grove, CA: Thomson Learning.

Cohen, J. (1994). The earth is around (p < .05). American Psychologist, 49(12), 997–1003.

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference and Prediction (2nd ed.). New York: Springer.

Hastie, T., Tibshirani, R., & Wainwright, M. (2015). Statistical Learning with Sparsity: The Lasso and Generallizations. New York: Chapman and Hall Book.

Isik, O., Kosaroglu, S., & Demirci, A. (2018). The impact of size and growth decision on Turkish banks' profitability. International Journal of Economics and Finance Issues, 8(1), 21–29.

Lin, X., & Zhang, Y. (2009). Bank ownership reform and bank performance in China. Journal of Banking and Finance, 33(1), 20–29.

Nguyen, H. (2016). Why p-value are banned?. Thai Statistician, 14(2), i–iv.

Nguyen, H. (2019). How to test without p-value?. Thai Statistician 17(2), i–x.

Rahman, A., & Reja, B. (2015). Ownership structure and bank performance. Journal of Economic, Business and Management, 3(5), 483–488.

Swai, J., & Mbogela, C. (2014). Do ownership structure affect banks' performance? An empirical inquiry onto Tanzanian bank industry. Journal of Finance and Risk Perspectives, 3(2), 47–66.

Tibshirani, R. (1996). Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society, Series B (Methodological), 58(1), 267–288.

Wooldridge, J. M. (2012). Introductory Econometrics: A Modern Approach (5th ed). USA: Cengage Learning.

Published

2020-09-14

Issue

Section

Articles

How to Cite

Bùi Thị Thiện, M. (2020). Phương pháp ước lượng LASSO: Cơ sở toán học và ứng dụng. JOURNAL OF ASIAN BUSINESS AND ECONOMIC STUDIES, 31(4), 05-22. https://doi.org/10.24311/jabes/2020.31.04.4