Robust estimation with the weighted trimmed likelihood estimator

Chalabi, Yohan and Wuertz, Diethelm (2012): Robust estimation with the weighted trimmed likelihood estimator.

Abstract

We consider the problem related to the estimation of parametric models in the presence of outliers. The maximum likelihood estimator is often used to find parameter values. However, it is highly sensitive to abnormal points. In this regard, the weighted trimmed likelihood estimator (WTLE) has been introduced as a robust alternative. We present a new scheme for automatically computing the trimming parameter and weights of the WTLE. The method is illustrated by applying it to the standard GARCH model. We compare the approach with other recently introduced robust GARCH estimators through an extensive simulation study.

• Item Type: MPRA Paper
• Language: English
• Keywords: GARCH models, Robust estimators, outliers, Weighted trimmed likelihood estimator (WTLE), Quasi maximum Likelihood estimator (QMLE)
• Subjects: C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General > C13 - Estimation: General; C - Mathematical and Quantitative Methods > C2 - Single Equation Models ; Single Variables > C22 - Time-Series Models ; Dynamic Quantile Regressions ; Dynamic Treatment Effect Models ; Diffusion Processes

References

T. Bednarski and B. Clarke. Trimmed likelihood estimation of location and scale of the normal distribution. Australian Journal of Statistics, 35(2):141–153, 1993.

T. Bollerslev. Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3):307–327, Apr. 1986.

T. Bollerslev. Glossary to ARCH (GARCH). Feb. 2009.

C. Brooks, S. Burke, and G. Persand. Benchmarks and the accuracy of GARCH model estimation. International Journal of Forecasting, 17(1):45–56, 2001.

A. Charles and O. Darne. Outliers and GARCH models in financial data. Economics Letters, 86(3):347–352, Mar. 2005.

R. C. H. Cheng and N. A. K. Amin. Estimating parameters in continuous univariate distributions with a shifted origin. Journal of the Royal Statistical Society. Series B (Methodological), 45 (3):394–403, 1983.

P. Cizek. Greneral trimmed estimation: robust approach to nonlinear and limited dependent variable models. Econometric Theory, 24(06):1500–1529, 2008.

H. David and H. Nagaraja. Order statistics. NJ: John Wiley & Sons, 7:159–61, 2003.

R. Dimova and N. Neykov. Generalized d-fullness techniques for breakdown point study of the trimmed likelihood estimator with applications. Theory and applications of recent robust methods, pages 83–91, 2004.

R. Engle. Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica, 50(4):987–1007, 1982.

R. A. Fisher. On the mathematical foundations of theoretical statistics. Lond. Phil. Trans. (A), 223:1–33, 1922.

A. Hadi and A. Luceño. Maximum trimmed likelihood estimators: a unified approach, examples, and algorithms. Computational Statistics & Data Analysis, 25(3):251–272, 1997.

L. Hotta and R. Tsay. Outliers in GARCH processes, 1998.

C.-J. Kim. Dynamic linear models with Markov-switching. Journal of Econometrics, 60(1–2): 1–22, 1994.

C. Kuan. Lecture on the Markov switching model. Institute of Economics Academia Sinica, 2002.

M. Markatou. Mixture models, robustness, and the weighted likelihood methodology. Biometrics, 56(2):483–486, 2000.

B. Mendes. Assessing the bias of maximum likelihood estimates of contaminated GARCH models. Journal of Statistical Computation and Simulation, 67(4):359–376, 2000.

N. Muler and V. Yohai. Robust estimates for GARCH models. Journal of Statistical Planning and Inference, 138(10):2918–2940, 2008.

C. Müller and N. Neykov. Breakdown points of trimmed likelihood estimators and related estimators in generalized linear models. Journal of Statistical Planning and Inference, 116(2): 503–519, 2003.

N. Neykov and C. Müller. Breakdown point and computation of trimmed likelihood estimators in generalized linear models. Developments in robust statistics. Physica-Verlag, Heidelberg, pages 277–286, 2003.

N. Neykov and P. Neytchev. A robust alternative of the maximum likelihood estimators. COMPSTAT 1990 - Short Communications, pages 99–100, 1990.

N. Neykov, P. Filzmoser, R. Dimova, and P. Neytchev. Robust fitting of mixtures using the trimmed likelihood estimator. Computational Statistics & Data Analysis, 52(1):299–308, 2007.

R. Pyke. Spacings. Journal of the Royal Statistical Society. Series B (Methodological), pages 395–449, 1965.

R Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria.

B. Ranneby. The maximum spacing method. An estimation method related to the maximum likelihood method. Scandinavian Journal of Statistics, 11(2):93–112, 1984.

D. Vandev and N. Neykov. New directions in statistical data analysis and robustness, chapter Robust maximum likelihood in the gaussian case, pages 257–264. Birkhauser Verlag, 1993.

D. Vandev and N. Neykov. About regression estimators with high breakdown point. Statistics, 32(2):111–129, 1998.