SIMULATION STUDY ON THE ESTIMATION METHODS FOR A JOINED POINT IN TOBIT-PIECEWISE REGRESSION

ผู้แต่ง

  • Titirut Thipbharos Faculty of Applied Science, Dhurakij Pundit University

คำสำคัญ:

Outliers, Tobit-piecewise regression, LS, MLE

บทคัดย่อ

The objective of this study is to introduce the estimation of a joined point in Tobit-piecewise regression model (Mekbunditkul, 2010). There are two interested methods, in this paper, introduced to estimate unknown joined point in Tobit-piecewise regression in the case of observed data containing outliers. Those are based on Quandt’s method which is one of the maximum likelihood method and on Levenberg-Marquardt method which is one of nonlinear least square based. Simulation study is provided to compare the potential applicability of each estimator which is considered in terms of the average sum of squares of residuals (ASSR) (Mekbunditkul, 2010). It is found that Tobit-piecewise regression model when the unknown joined point is estimated by LS method yields non-significant smaller ASSR than by ML method in every situation according to the simulation study.

References

Goldfeld, S.M., Kelejian, H.H. and Quandt, R.E. (1971). Least Squares and Maximum Likelihood Estimation of Switching Regressions. Econometric Research Program. 130 (November).

Hudson, D.J. (1966). Fitting Segmented Curves Whose Join Points Have to be Estimated. Journal of the American Statistical Association, 61, 1097-1129.

Jöreskog, K.G. (2002). Censored Variables and Censored Regression. (Online). Available at http://www.ssicentral.com/lisrel/techdocs/censor.pdf

Marquardt, D. (1963). An Algorithm for Least-Squares Estimation of Nonlinear Parameters. SIAM Journal on Applied Mathematics, 11, 431–441.

Mekbunditkul, T. (2010). An Alternative Estimator of Regression Coefficient with Outliers (Doctoral dissertation). National Institute of Development Administration.

Poon,K.S. et. al. (2008). Analysis of structural change-point in multivariate regression models. An application on IT productivity impact.

Quandt, R.E. (1958). The estimation of the Parameters of a Linear Regression System Obeying Two Separate Regimes. Journal of the American Statistical Association, 53, 873-880.

Rosett, R.N. and Nelson, F.D. (1975). Estimation of the two-limit Probit regression model. Econometrica, 43, 141–146.

Rousseeuw, P.J. and Leroy, A. M. (1987). Robust Regression and Outlier detection. New York : John Wiley & Sons.

Suits, D., Marson, A. and Chan, L. (1978). Spline Functions Fitted by Standard Regression Methods. Review of Economics and Statistics. 132 – 139.

Tobin, J. 1958. Estimation of Relationships for Limited Dependent Variables. Econometrica. 26, 24-36.

Downloads

เผยแพร่แล้ว

2020-07-20