On robust local polynomial estimation with long-memory errors

Prediction in time series models with a trend requires reliable estima- tion of the trend function at the right end of the observed series. Local polynomial smoothing is a suitable tool because boundary corrections are included implicitly. However, outliers may lead to unreliable estimates, if least squares regression is used. In this paper, local polynomial smoothing based on M-estimators are asymptotically equivalent to the least square solution, under the (ideal) Gaussian model. Outliers turn out to have a major effect on nonrobust bandwidht selection, in particular due to the change of the dependence structure.

[1]  H. Müller,et al.  Local Polynomial Modeling and Its Applications , 1998 .

[2]  Jan Beran,et al.  Data-driven estimation of semiparametric fractional autoregressive models , 2000 .

[3]  J. Beran.  SEMIFAR models - a semiparametric framework for modelling trends, long-range dependence and nonstationarity , 2000 .

[4]  C. Granger,et al.  AN INTRODUCTION TO LONG‐MEMORY TIME SERIES MODELS AND FRACTIONAL DIFFERENCING , 1980 .

[5]  Jan Beran,et al.  Local Polynomial Fitting with Long-Memory, Short-Memory and Antipersistent Errors , 2002 .

[6]  M. Wand,et al.  Multivariate Locally Weighted Least Squares Regression , 1994 .

[7]  B. Ray,et al.  Bandwidth selection for kernel regression with long-range dependent errors , 1997 .

[8]  Jan Beran,et al.  Statistics for long-memory processes , 1994 .

[9]  Jan Beran,et al.  SEMIFAR models|a semiparametric approach to modelling trends , 2002 .

[10]  J. Beran.  M Estimators of Location for Gaussian and Related Processes With Slowly Decaying Serial Correlations , 1991 .

[11]  Nonparametric trend estimation in replicated time series , 2001 .

[12]  J. Beran.  Statistical methods for data with long-range dependence , 1992 .

[13]  C. Jennison,et al.  Robust Statistics: The Approach Based on Influence Functions , 1987 .

[14]  Yoshihiro Yajima,et al.  A CENTRAL LIMIT THEOREM OF FOURIER TRANSFORMS OF STRONGLY DEPENDENT STATIONARY PROCESSES , 1989 .

[15]  Hira L. Koul,et al.  Asymptotic normality of regression estimators with long memory errors , 1996 .

[16]  Jan Beran,et al.  SEMIFAR forecasts, with applications to foreign exchange rates , 1999 .

[17]  Jan Beran,et al.  Nonparametric M-estimation with long-memory errors , 2000 .