Reducing The Influence of High Leverage Points in Beta Regression Using The Gm6 Robust Estimator

  • Hamza Lateef Katea Al-Ayashy Department of Statistics, College of Administration and Economics, University of Al-Qadisiyah, Al-Qadisiyah, Iraq
  • Taha Alshaybawee Department of Statistics, College of Administration and Economics, University of Al-Qadisiyah, Al-Qadisiyah, Iraq
Keywords: Beta regression, GM6-BR-resistant estimation, high leverage points, outliers

Abstract

The problem of outliers and high leverage points is one of the most prominent challenges facing the design of statistical models, especially in regression models, as they have a significant impact on distorting the results of statistical estimation. This research aims to address the impact of high leverage points in a beta regression model using robustness estimation methods, specifically the GM6 multistage estimator (GM6-BR). A comparison of four estimation methods was studied: traditional estimation (BR), least discrete squares estimator (LTS-BR), generalized estimation (GM-BR), and GM6-BR. A simulation study was conducted on two models: one linear and the other nonlinear, with data contamination of 10% and 20% introduced to test the robustness of the different methods. The results demonstrated a clear superiority of the GM6-BR method in terms of reducing error (RMSE, MAE) and skewness (BIAS), while maintaining stability in the presence of contamination. Practical application on real data also showed that GM6-BR was least affected by outliers compared to other methods, while the traditional BR method exhibited the highest level of distortion. Therefore, the study recommends adopting GM6-BR as an effective and accurate option for analyzing data containing high leverage points or outliers, especially within beta regression models.

References

M. R. Abonazel, I. Dawoud, F. A. Awwad, and A. F. Lukman, “Dawoud–Kibria Estimator for Beta Regression Model: Simulation and Application,” Frontiers in Applied Mathematics and Statistics, vol. 8, p. 775068, 2022.

M. R. Abonazel and I. M. Taha, “Beta Ridge Regression Estimators: Simulation and Application,” Commun. Stat. Simul. Comput., vol. 52, no. 9, pp. 4280–4292, 2023.

H. L. K. Al-ayashy and T. Alshaybawee, “New Robust Beta Regression Estimation to Overcome the Effect of High Leverage Points,” 2025.

F. M. Bayer and F. Cribari-Neto, “Model Selection Criteria in Beta Regression with Varying Dispersion,” Commun. Stat. Simul. Comput., vol. 46, no. 1, pp. 729–746, 2017.

F. Cribari-Neto and A. Zeileis, “Beta Regression in R,” J. Stat. Softw., vol. 34, pp. 1–24, 2010.

Z. M. A. El-Raoof, M. M. El-Gohary, and E. G. Yehia, “Robust Estimation for Beta Regression Model in the Presence of Outliers: A Comparative Study,” Al-Tijarah wal-Tamwil, vol. 43, no. 3, pp. 380–406, 2023.

P. L. Espinheira, S. L. P. Ferrari, and F. Cribari-Neto, “On Beta Regression Residuals,” J. Appl. Stat., vol. 35, no. 4, pp. 407–419, 2008.

P. L. Espinheira, L. C. M. da Silva, A. de O. Silva, and R. Ospina, “Model Selection Criteria on Beta Regression for Machine Learning,” Mach. Learn. Knowl. Extr., vol. 1, no. 1, p. 26, 2019.

P. L. Espinheira, L. C. M. da Silva, and A. de O. Silva, “Prediction Measures in Beta Regression Models,” ArXiv Preprint ArXiv:1501.04830, 2015.

S. Ferrari and F. Cribari-Neto, “Beta Regression for Modelling Rates and Proportions,” J. Appl. Stat., vol. 31, no. 7, pp. 799–815, 2004.

Ghosh, “Robust Inference under the Beta Regression Model with Application to Health Care Studies,” Stat. Methods Med. Res., vol. 28, no. 3, pp. 871–888, 2019, doi: 10.1177/0962280217738142.

R. W. Hill, “Robust Regression When There Are Outliers in the Carriers,” 1977.

P. Karlsson, K. Månsson, and B. M. G. Kibria, “A Liu Estimator for the Beta Regression Model and Its Application to Chemical Data,” J. Chemom., vol. 34, no. 10, p. e3300, 2020.

Y. S. Maluf, S. L. P. Ferrari, and F. F. Queiroz, “Robust Beta Regression through the Logit Transformation,” Metrika, pp. 1–21, 2024.

R. Ospina, S. G. F. Baltazar, V. Leiva, J. Figueroa-Zúñiga, and C. Castro, “Robust Semi-Parametric Inference for Two-Stage Production Models: A Beta Regression Approach,” Symmetry, vol. 15, no. 7, p. 1362, 2023.

R. Ospina, F. Cribari-Neto, and K. L. P. Vasconcellos, “Improved Point and Interval Estimation for a Beta Regression Model,” Comput. Stat. Data Anal., vol. 51, no. 2, pp. 960–981, 2006.

T. K. A. Ribeiro and S. L. P. Ferrari, “Robust Estimation in Beta Regression via Maximum L Q-Likelihood,” Stat. Pap., vol. 64, no. 1, pp. 321–353, 2023.

P. J. Rousseeuw and K. Van Driessen, “A Fast Algorithm for the Minimum Covariance Determinant Estimator,” Technometrics, vol. 41, no. 3, pp. 212–223, 1999.

P. J. Rousseeuw and A. M. Leroy, Robust Regression and Outlier Detection, Hoboken, NJ, USA: John Wiley & Sons, 2003.

K. L. P. Vasconcellos and F. Cribari-Neto, “Improved Maximum Likelihood Estimation in a New Class of Beta Regression Models,” Braz. J. Probab. Stat., pp. 13–31, 2005.

H. Zhou and X. Huang, “Bayesian Beta Regression for Bounded Responses with Unknown Supports,” Comput. Stat. Data Anal., vol. 167, p. 107345, 2022.

Published
2025-06-22
How to Cite
Al-Ayashy, H. L. K., & Alshaybawee, T. (2025). Reducing The Influence of High Leverage Points in Beta Regression Using The Gm6 Robust Estimator. CENTRAL ASIAN JOURNAL OF MATHEMATICAL THEORY AND COMPUTER SCIENCES, 6(3), 614-631. Retrieved from https://cajmtcs.centralasianstudies.org/index.php/CAJMTCS/article/view/790
Section
Articles