Research Article
BibTex RIS Cite

Tukey M Dayanıklı Regresyon Yönteminin Çoklu Doğrusal Bağlantıya Karşı Zafiyeti

Year 2023, Volume: 27 Issue: 1, 84 - 89, 25.04.2023
https://doi.org/10.19113/sdufenbed.1141519

Abstract

Bu çalışmada, Tukey M dayanıklı regresyon metodunun, çoklu doğrusal bağlantı problemine sahip veri setleri için bir çözüm sunup sunmadığı araştırılmıştır. Çalışmada açıklayıcı değişkenler arasında çoklu doğrusal bağlantı göstergesi olan yüksek VIF (varyans şişirme faktörü) değerlerinin, artık değerler üstünden çalışan dayanıklı metotlarla kontrol edilemediği gözlenmiştir. Bunun sebebi çoklu doğrusal bağlantının ve bunun sonucu olan yüksek VIF değerlerinin ekstrem artık değerler üretmiyor olmasıdır. Dolayısıyla dayanıklı metotlar yüksek VIF problemine bir çözüm sunamamaktadır. Bu durum kapsamlı bir simülasyon çalışması ile gösterilmiştir. Simülasyon çalışmasında üç farklı korelasyon değeri için üç değişkenli normal dağılıma sahip açıklayıcı değişkenler üretilmiştir. Çalışmada ayrıca iki gerçek hayat veri örneği kullanılmış ve sonuçların simülasyon bulgularını desteklendiği görülmüştür. Tüm bu sebeplerden dolayı çoklu doğrusal bağlantı durumunda özel yöntemlerin kullanılması gerektiği sonucunu çıkarabiliriz.

References

  • [1] Hocking, R.R., Pendleton, O.J. 1983. The regression dilemma. Commun. Stat. Theory Methods, 12(5), 497-527.
  • [2] Mansfield, E.R., Helms, B.P. 1982. Detecting multicollinearity. Am. Stat., 36, 158-160.
  • [3] Kutner, M.H., Nachtsheim, C.J., Neter, J., Li, W. 2004. Applied Linear Statistical Models, 5th edn. McGraw Hill, New York.
  • [4] Chatterjee, S., Hadi, A.S. 2012. Regression Analysis by Example, 5th edn. John Wiley and Sons, New Jersey.
  • [5] Marquaridt, D.W. 1970. Generalized inverses, ridge regression, biased linear estimation, and nonlinear estimation. Technometrics 12(3), 591-612.
  • [6] Belsley, D.A., Klema, V.C. 1974. Detecting and assessing the problems caused by multicollinearity: A use of the singular-value decomposition. NBER Working Paper Series, 66.
  • [7] Belsley, D.A., Kuh, E., Welsch, R.E. 1980. Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. John Wiley and Sons, New York.
  • [8] Montgomery, D.C., Askin, R.G. 1981. Problems of nonnormality and multicollinearity for forecasting methods based on least squares. AIIE Trans. 13(2), 102-115.
  • [9] Hoerl, A.E., Kennard, R.W. 1970. Ridge regression. Biased estimation for nonorthogonal problems. Technometrics. 12(1), 55-67.
  • [10] Holland, P.W. 1973. Weighted Ridge Regression: Combining Ridge and Robust Regression Methods. NBER Working Paper Series. 11.
  • [11] Askin, R.G., Montgomery, D.C. 1980. Augmented Robust Estimators. Technometrics. 22, 333-341.
  • [12] Yu, C., Yao, W. 2017. Robust linear regression: A review and comparison. Communications in Statistics - Simulation and Computation. 46(8), 6261-6282.
  • [13] Huber, P.J. 1964. Robust estimation of a location parameter. Ann. Math. Stat. 35, 73-101.
  • [14] Elsaid, H., Fried, R. 2015. Tukey’s M-estimator of the Poisson parameter with a special focus on small means. Stat. Methods Appl. 25, 191–209.
  • [15] Becker, R. A., Chambers, J. M., Wilks, A. R. 1988. The New S Language. Wadsworth & Brooks/Cole.

Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity

Year 2023, Volume: 27 Issue: 1, 84 - 89, 25.04.2023
https://doi.org/10.19113/sdufenbed.1141519

Abstract

In this study, we investigate whether the Tukey M robust regression method provides a solution for the data sets suffering from multicollinearity problem. It is observed that high values of variance inflation factors (VIF) which is a sign of the multiple linear link among the explanatory variables, cannot be controlled by the robust methods which work through the residual values. The reason for this fact is that multicollinearity and high values of VIF which is a result of multicollinearity do not produce extreme residuals. For this reason, the robust methods cannot provide a solution for the high VIF problem. This fact is shown by an extensive simulation study. In the simulation study, the explanatory variables were derived from trivariate normal distribution for three different correlation values. In this study, we also used two real-life data examples and we observed that the results support the findings of the simulation study. For all these reasons, we can conclude that specialized methods should be utilized in the case of multicollinearity.

References

  • [1] Hocking, R.R., Pendleton, O.J. 1983. The regression dilemma. Commun. Stat. Theory Methods, 12(5), 497-527.
  • [2] Mansfield, E.R., Helms, B.P. 1982. Detecting multicollinearity. Am. Stat., 36, 158-160.
  • [3] Kutner, M.H., Nachtsheim, C.J., Neter, J., Li, W. 2004. Applied Linear Statistical Models, 5th edn. McGraw Hill, New York.
  • [4] Chatterjee, S., Hadi, A.S. 2012. Regression Analysis by Example, 5th edn. John Wiley and Sons, New Jersey.
  • [5] Marquaridt, D.W. 1970. Generalized inverses, ridge regression, biased linear estimation, and nonlinear estimation. Technometrics 12(3), 591-612.
  • [6] Belsley, D.A., Klema, V.C. 1974. Detecting and assessing the problems caused by multicollinearity: A use of the singular-value decomposition. NBER Working Paper Series, 66.
  • [7] Belsley, D.A., Kuh, E., Welsch, R.E. 1980. Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. John Wiley and Sons, New York.
  • [8] Montgomery, D.C., Askin, R.G. 1981. Problems of nonnormality and multicollinearity for forecasting methods based on least squares. AIIE Trans. 13(2), 102-115.
  • [9] Hoerl, A.E., Kennard, R.W. 1970. Ridge regression. Biased estimation for nonorthogonal problems. Technometrics. 12(1), 55-67.
  • [10] Holland, P.W. 1973. Weighted Ridge Regression: Combining Ridge and Robust Regression Methods. NBER Working Paper Series. 11.
  • [11] Askin, R.G., Montgomery, D.C. 1980. Augmented Robust Estimators. Technometrics. 22, 333-341.
  • [12] Yu, C., Yao, W. 2017. Robust linear regression: A review and comparison. Communications in Statistics - Simulation and Computation. 46(8), 6261-6282.
  • [13] Huber, P.J. 1964. Robust estimation of a location parameter. Ann. Math. Stat. 35, 73-101.
  • [14] Elsaid, H., Fried, R. 2015. Tukey’s M-estimator of the Poisson parameter with a special focus on small means. Stat. Methods Appl. 25, 191–209.
  • [15] Becker, R. A., Chambers, J. M., Wilks, A. R. 1988. The New S Language. Wadsworth & Brooks/Cole.
There are 15 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Makaleler
Authors

Filiz Karadağ 0000-0002-0116-7772

Hakan Savaş Sazak 0000-0001-6123-1214

Publication Date April 25, 2023
Published in Issue Year 2023 Volume: 27 Issue: 1

Cite

APA Karadağ, F., & Sazak, H. S. (2023). Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 27(1), 84-89. https://doi.org/10.19113/sdufenbed.1141519
AMA Karadağ F, Sazak HS. Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity. J. Nat. Appl. Sci. April 2023;27(1):84-89. doi:10.19113/sdufenbed.1141519
Chicago Karadağ, Filiz, and Hakan Savaş Sazak. “Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity”. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi 27, no. 1 (April 2023): 84-89. https://doi.org/10.19113/sdufenbed.1141519.
EndNote Karadağ F, Sazak HS (April 1, 2023) Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi 27 1 84–89.
IEEE F. Karadağ and H. S. Sazak, “Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity”, J. Nat. Appl. Sci., vol. 27, no. 1, pp. 84–89, 2023, doi: 10.19113/sdufenbed.1141519.
ISNAD Karadağ, Filiz - Sazak, Hakan Savaş. “Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity”. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi 27/1 (April 2023), 84-89. https://doi.org/10.19113/sdufenbed.1141519.
JAMA Karadağ F, Sazak HS. Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity. J. Nat. Appl. Sci. 2023;27:84–89.
MLA Karadağ, Filiz and Hakan Savaş Sazak. “Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity”. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol. 27, no. 1, 2023, pp. 84-89, doi:10.19113/sdufenbed.1141519.
Vancouver Karadağ F, Sazak HS. Vulnerability of the Tukey M Robust Regression Method Against Multicollinearity. J. Nat. Appl. Sci. 2023;27(1):84-9.

e-ISSN :1308-6529
Linking ISSN (ISSN-L): 1300-7688

All published articles in the journal can be accessed free of charge and are open access under the Creative Commons CC BY-NC (Attribution-NonCommercial) license. All authors and other journal users are deemed to have accepted this situation. Click here to access detailed information about the CC BY-NC license.