Beta Principal Component Regression Model with Application

  • Rammah Oday Hassan Assistant Lecturer of Statistic at Administration and Economics of Babylon University, Iraq
Keywords: Beta Regression, Principal Component Regression, Multicollinearity, Beta Principal Component Regression

Abstract

The main goal of regression analysis is to estimate the effect relationship between independent variables and the dependent variable. Consequently, the type of response variable data determines the type of regression model to be used. If the dependent variable data is continuous and represents proportions confined between (0, 1), the Beta regression model is considered a good choice for representing such a relationship. However, at times, the Beta regression model encounters issues that make the estimated relationship unstable. This instability is due to the presence of some econometric problems that cause the estimators to be inaccurate. One such issue is multicollinearity. This problem arises when there is a strong correlation between the explanatory variables, which particularly affects the estimators of the parameters (β) by reducing their accuracy. Multicollinearity leads to an unusual inflation of parameter variances, making the estimators less reliable. In this paper, we will present a new method that integrates the Beta regression model with Principal Component Regression to develop a hybrid regression model. This hybrid model will be more suitable for estimation in the presence of multicollinearity issues. Simulation examples and real data are used to evaluate the performance of the proposed method in comparison with existing methods.

References

[1] F. H. H. Alhusseini and M. H. Odah, "Principal component regression for tobit model and purchases of gold," in Proc. 10th Int. Manag. Conf., Bucharest, Romania, vol. 10, pp. 491–500, 2016.
[2] W. F. Massy, "Principal components regression in exploratory statistical research," J. Amer. Stat. Assoc., vol. 60, no. 309, pp. 234–256, 1965.
[3] M. Greenacre, P. J. Groenen, T. Hastie, A. I. d’Enza, A. Markos, and E. Tuzhilina, "Principal component analysis," Nat. Rev. Methods Primers, vol. 2, no. 1, p. 100, 2022.
[4] W. F. Massy, "Principal components regression in exploratory statistical research," J. Amer. Stat. Assoc., vol. 60, no. 309, pp. 234–256, 1965.
[5] A. Junaid, A. Khan, A. Alrumayh, F. M. Alghamdi, E. Hussam, H. M. Aljohani, and A. Alrashidi, "Modified two parameter ridge estimator for beta regression model," J. Radiat. Res. Appl. Sci., vol. 17, no. 2, p. 100905, 2024.
[6] S. H. Mahmood, "Estimating models and evaluating their efficiency under multicollinearity in multiple linear regression: A comparative study," Zanco J. Human Sci., vol. 28, no. 5, pp. 264–277, 2024.
[7] A. Kalnins, "Multicollinearity: How common factors cause Type 1 errors in multivariate regression," Strateg. Manag. J., vol. 39, no. 8, pp. 2362–2385, 2018.
[8] M. R. Abonazel, H. A. Said, E. Tag-Eldin, S. Abdel-Rahman, and I. G. Khattab, "Using beta regression modeling in medical sciences: a comparative study," Commun. Math. Biol. Neurosci., Article ID, 2023.
[9] F. Bertrand, N. Meyer, K. El Bayed, I. J. Namer, and M. Maumy-Bertrand, "Regression beta PLS," J. Soc. Fr. Stat., vol. 154, no. 3, pp. 143–159, 2013.
[10] M. R. Abonazel, H. A. Said, E. Tag-Eldin, S. Abdel-Rahman, and I. G. Khattab, "Using beta regression modeling in medical sciences: a comparative study," Commun. Math. Biol. Neurosci., Article ID, 2023.
[11] E. A. Geissinger, C. L. Khoo, I. C. Richmond, S. J. Faulkner, and D. C. Schneider, "A case for beta regression in the natural sciences," Ecosphere, vol. 13, no. 2, p. e3940, 2022.
[12] S. L. P. Ferrari and F. Cribari-Neto, "Beta regression for modelling rates and proportions," J. Appl. Stat., vol. 31, no. 7, pp. 799–815, 2004.
[13] M. R. Abonazel, H. A. Said, E. Tag-Eldin, S. Abdel-Rahman, and I. G. Khattab, "Using beta regression modeling in medical sciences: a comparative study," Commun. Math. Biol. Neurosci., Article ID, 2023.
[14] R. A. Belaghi, Y. Asar, and R. Larsson, "Improved shrinkage estimators in the beta regression model with application in econometric and educational data," Stat. Papers, vol. 64, no. 6, pp. 1891–1912, 2023.
[15] M. D. Ismaiel and A. D. Ahmed, "Comparison between estimates of beta regression model using MSE," J. Econ. Admin. Sci., vol. 30, no. 143, pp. 523–535, 2024.
[16] Q. A. Owoyemi and A. Bolakale, "Comparative analysis of some linear predictive models in the presence of multicollinearity," Int. J. Adv. Stat. Probab., vol. 11, no. 1, 2023.
[17] H. Ali, C. N. Akanihu, and J. Felix, "Investigating the parameters of the beta distribution," World J. Adv. Res. Rev., vol. 19, no. 1, pp. 815–830, 2023.
[18] C. F. Damgaard and K. M. Irvine, "Using the beta distribution to analyse plant cover data," J. Ecol., vol. 107, no. 6, pp. 2747–2759, 2019.
[19] F. Cribari-Neto and A. Zeileis, "Beta regression in R," J. Stat. Softw., vol. 34, pp. 1–24, 2010.
[20] L. Firinguetti, M. González-Navarrete, and R. Machaca-Aguilar, "Shrinkage estimators for beta regression models," arXiv preprint, arXiv:2406.18047, 2024.
Published
2025-06-18
How to Cite
Hassan , R. O. (2025). Beta Principal Component Regression Model with Application. CENTRAL ASIAN JOURNAL OF MATHEMATICAL THEORY AND COMPUTER SCIENCES, 6(3), 591-600. Retrieved from https://cajmtcs.centralasianstudies.org/index.php/CAJMTCS/article/view/787
Section
Articles