Robust Estimation of Generalized Estimating Equation when Data Contain Outliers

Khoirin Nisa, Netti Herawati

Abstract


Abstract—In this paper, a robust procedure for estimating parameters of regression model when generalized estimating equation (GEE) applied to longitudinal data that contains outliers is proposed. The method is called ‘iteratively reweighted least trimmed square’ (IRLTS) which is a combination of the iteratively reweighted least square (IRLS) and least trimmed square (LTS) methods. To assess the proposed method a simulation study was conducted and the result shows that the method is robust against outliers.

Keywords—GEE, IRLS, LTS, longitudinal data, regression model.


Full Text:

PDF

References


P. McCullagh and J.A. Nelder, Generalized Linear Models. London : Chapmann and Hall, 1989.

K.Y. Liang and S.L. Zeger, “Longitudinal data analysis using generalized linear models”, Biometrika, vol 73, pp. 13-22, 1986.

B.F. Qaqish and J.S. Preisser, “Resistant fits for regression with correlated outcomes an estimating equations approach”, Journal of Statistical Planning and Inference, vol. 75, pp. 15-431, 1999.

P.S. Gill, “A Robust Mixed Linear Model Analysis for Longitudinal Data”, Statistics in Medicine, vol. 19, pp. 975-987, 2000.

S.H. Jung and Z. Ying, “Rank-Based Regression With Repeated Measurements Data”, Biometrika, vol. 90, pp. 732-740, 2003.

Abebe, A., McKean, J. W. & Kloke, J. D., Bilgic, Y. “Iterated Reweighted Rank-Based Estimates for GEE Models”, submitted.

R.J. Rousseeuw and A.M. Leroy, Robust Regression and Outlier Detection. New York: Wiley, 1987.

J.A. Víšek, “The Least Trimmed Squares – random carriers”. Bulletin of the Czech Econometric Society, vol. 6, pp. 1-30, 1999.

J.A. Víšek, The Least Trimmed Squares. Part II: √n-consistency. Kybernetika, vol. 42, pp. 181-202, 2006a.

J.A. Víšek, “The Least Trimmed Squares. Part III: Asymptotic normality”. Kybernetika, vol. 42, pp. 203-224, (2006b).

P.J. Rousseeuw, and K. van Driessen, “ Computing LTS Regression for Large Data Sets”. Data mining and Knowledge Discovery, vol. 12, pp. 29-45, 2006.




DOI: http://dx.doi.org/10.23960/ins.v2i1.23


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
View My Stats
Flag Counter