Studying the most important factors affecting stroke by using some penal regulation methods
DOI:
https://doi.org/10.36322/jksc.176(G).20052Keywords:
Linear Regression , Penalized Regression Methods, StrokeAbstract
In this paper the concept of variable selection method was studied by employing the penalty method in the multiple linear regression model. Four organizing methods (parts) were dealt with, and these methods are (the ridge method, the lasso method, the adaptive lasso method, and the elastic net method). Each penalty method was also clarified by studying its mathematical formula, as well as the most important characteristics and defects of each method.
In order to study these methods, three simulated experiments were conducted. In each experiment, it was assumed that there is a real vector for the parameters whose values are to be estimated in order to measure the accuracy of the work of each method. Among them, in addition to that, the conversion of the observations of the response variable into central values was performed, that is, the study assumed that there are different values of the correlations between the explanatory variables. The results of the simulation experiments indicated that the elastic net method showed the lowest value for the standard of feature estimation quality called the standard of mean absolute differences, and therefore this method can be considered the best method in terms of accuracy and interpretation of the model.
In order to demonstrate the efficiency of the work of the penalty methods mentioned above, real data collected by the researcher from Al-Nasiriyah Teaching Hospital were analyzed to represent a sample of patients with stroke, given that the response variable in this study represents the size of the stroke and a group of (17) explanatory variables, and the representation of the relationship between Stroke size variable and explanatory variables using a multiple linear regression model in order to identify the most important factors or variables that affect the size of stroke. The results also showed that the elastic net method is the best penalty method, whether at the level of choosing the variables or at the level of the explanatory ability of the model.
Downloads
References
المراجع:
] Ann Kirkland , Lisa, (2014),”LASSO Simultaneous shrinkage and selection via L_1-norm” , A thesis in the Mathematical Statistics,University of Preroria, Faculty of Natural and Agricultural Sciences.
[2] Chatterjee, S., & Hadi, A. S. (2006). Regression analysis by example. John Wiley & Sons.
[3] Hoerl, A.E. and Kennard, R.W. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technimetrics, 12(1):55-67.
[4] Li, C., Pak, D., & Todem, D. (2020). Adaptive lasso for the Cox regression with interval censored and possibly left truncated data. Statistical Methods in Medical Research, 29(4), 1243-1255.
[5] Liu, Y. (2022). Adaptive lasso variable selection method for semiparametric spatial autoregressive panel data model with random effects. Communications in Statistics-Theory and Methods, 1-19.
[6] Tibshirani, R., Saunders, M., Rosset, S., Zhu, J. and Knight, K. (2005). Sparsity and smoothness via the fused LASSO. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(1):91-108.
[7] Tibshirani. R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B (Methodological). 267-288.
[8] Zhao, P., Rocha, G. and Yu. B. (2009). The composite absolute penalties famil for grouped and hierarchical variable Selection. The Annals of Statistics, 37(6A):3468-3497.
[9] Zou, H. and Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2):301-320.
[10] Zou, H. and Zhang, H.H. (2009).On the adaptive elastic-net with a diverging number of parameters. The Annals of Statistics, 37(4):1733-1751.
[11] Zou, H.(2006). The adaptive LASSO and its oracle properties. Journal of the American Statistical Associa-fion, 101(476):1418-1429.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 أ.د. احمد نعيم فليح، الباحث حيدر ناظم محمد علي
This work is licensed under a Creative Commons Attribution 4.0 International License.
Permit others to distribute and copy the manuscript, to create extracts, abstracts, and other revised versions, adaptations, or derivative works of or from the manuscript (such as a translation), to include in a collective work, to text or data mine the article, even for commercial purposes, as long as they credit the author(s), do not represent the author as endorsing their adaptation of the article, and do not modify the article in such a way as to damage the author''''s honor or reputation. Further details are found at Creative Commons Attribution 4.0 International (CC BY 4.0)
How to Cite
