EFEKTIVITAS REGRESI KUANTIL DALAM MENGATASI PONTENSIAL PENCILAN
Abstract
Quantile regression as a robust regression method can be used to overcome the impact of unusual cases on regression estimates such as the presence of potential outliers in the data. The purpose of this study was to evaluate the effectiveness of quantile regression in dealing with potential outliers in multiple linear regression compared to ordinary least square (OLS). This study used simulation data in multiple regression model with the number of independent variables (p=3) for different sample sizes (n = 20, 40, 60, 100, 200) and and repeated 1000 times. The effectiveness of the quantile regression method and OLS in estimating β parameters was measured by Mean square error (MSE) and the best model is chosen based on the smallest Akaike Information Criterion (AIC) value. The results showed that in contrast to OLS, quantile regression was able to deal with potential outliers and provided a better estimator with a smaller mean mean square error. Compared to OLS and other quantiles, this study also provides sufficient results that quantile 0.5 provides the best parameter estimate and the best model based on the smallest MSE and AIC values.
Downloads
References
M.H. Kutner, C.J. Nachtsheim and J. Neter, Applied Linear Regression Models, 4th Ed., New York: McGraw-Hill Co. Inc., 2004.
D.C. Montgomery, E.A. Peck and G.G. Vining, Introduction to Linear Regression Analysis, 3rd Ed., USA: John Wiley & Sons, Inc., 2001.
N.R. Draper and H. Smith, Applied Regression Analysis, 3rd Ed., USA: John Wiley & Sons, Inc., 1998.
R. Koenker and K.F. Hallock, “Quantile regression,†Journal of Economic Perspectives, vol. 15, no.4, pp 143-156, 2001.
G.A.Haile and A.N. Nguyen, “Determinant of academic attainment in the United States: A quantile regression analysis of test scores, †Education Economics, vol. 16, pp. 29-57, 2008.
J. Staruss, K. Beege, B. Sikoki, A. Dwiyanto, Y. Herawati and F. Witoelar, The third wave of the Indonesia family life survey: Overview and field report, Santa Monica, CA: RAND Corp, 2004.
L. Hao and D.Q. Naiman, Quantile Regression, Thousand Oaks: Sage Publications Inc., 2007.
R. Koenker, Quantile regression, New York: Cambridge University Press, 2005.
R. Koenker and G. Bassett, “Regression quantile,†Econometrica, vol. 46, pp.33-50, 1978.
K. Nisa and N. Herawati, . ‘Robust Estimation of Generalized Estimating Equation when data contain outliers,’ Insist, vol. 2, No. 1, pp., 1-5, 2017.
P.J. Rousseeuw and A.M. Leroy, Robust Regression and Outlier Detection, New York: Wiley, 1987.
E. Setiawan, N. Herawati, K. Nisa, Nyusirwan, and S. Saidi, “Handling full multicollinearity and various numbers of outliers using robust ridge regression,†Sci.Int.(Lahore), vol 31, no. 2, pp. 201-204, 2019.
V. Barnett and T Lewis, Outlier in Statistical Data, New York :John Wiley & Sons, 1984.
W. Gilchrist, Statistical modelling with quantile functions, FL: Chapman and Hall/CRC, Boca Raton, 2000.
C.M. Kuan, An Introduction to Quantile Regression. Institute of Economics, Canada: Academia Sinica, 2007.
W.H. Greene, Econometric Analysis, 5th ed., New Jersey: Prentice Hall, 2002.
B. Fitzenverger, R. Koenker, J.A.F. Machado, (Eds.), Economic Applications of Quantile Regression, Berlin Heidelberg GmbH: Springer-Verlag, 2002.
M. Furno, Parameter Instability in Quantile Regressions, NewYork: Elsevier, 2007.
H. Akaike, Information theory and an extension of the maximum likelihood principle, In B.N. Petrow and F. Csaki (eds), Second International symposium on information theory (pp.267-281), Budapest: Academiai Kiado, 1973.
H. Akaike, “A new look at the statistical model identification,†IEEE Transactions on Automatic Control, vol. 19, pp.716-723, 1974.
R. Koenker, Quantreg: Quantile Regression, Version R package version 4.22, 2008.
Authors who publish with this Journal agree to the following terms:
- Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
- Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
- Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.
