Asymptotic robustness of least median of squares for autoregressions with additive outliers
- 1 January 1997
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 26 (10) , 2363-2380
- https://doi.org/10.1080/03610929708832053
Abstract
This paper considers the robustness properties in the time series context of the least median of squares (LMS) estimator. The influence function of the LMS estimator is derived under additive outlier contamination. This influence function is redescending and bounded for fixed values of the AR parameters. The gross-error sensitivity, however, is an unbounded function of the AR parameters. In order to asses the global robustness behavior of the LMS estimator, we consider several notions of breakdown. The breakdown points of the LMS estimator depend on the value of the underlying AR parameter. Generally, the breakdown point is below one half for high values of the AR parameter. The bias curves of the LMS estimator reveal, however, that the magnitude of outliers has to be considerable in order to cause breakdown.Keywords
This publication has 15 references indexed in Scilit:
- An outlier robust unit root test with an application to the extended Nelson-Plosser dataJournal of Econometrics, 1995
- Aspects of Robust Linear RegressionThe Annals of Statistics, 1993
- Lower Bounds for Contamination Bias: Globally Minimax Versus Locally Linear EstimationThe Annals of Statistics, 1993
- Robust Direction EstimationThe Annals of Statistics, 1992
- Robust Regression and Outlier DetectionPublished by Wiley ,1987
- Qualitative Robustness for Stochastic ProcessesThe Annals of Statistics, 1987
- Influence Functionals for Time SeriesThe Annals of Statistics, 1986
- Least Median of Squares RegressionJournal of the American Statistical Association, 1984
- Infinitesimal Robustness for Autoregressive ProcessesThe Annals of Statistics, 1984
- Some Aspects of Qualitative Robustness in Time SeriesPublished by Springer Nature ,1984