Summary
In this paper, we implement a new definition of breakdown in both finite and asymptotic samples with correlated observations arising from spatial statistics and time series. In such situations, existing definitions typically fail because parameters can sometimes breakdown to zero, i.e. the center of the parameter space. The reason is that these definitions center around defining an explicit critical region for either the parameter or the objective function. If for a particular outlier constellation the critical region is entered, breakdown is said to occur. In contrast to the traditional approach, we use a definition that leaves the critical region implicit but still encompasses all previous definitions of breakdown in linear and nonlinear regression settings. We provide examples involving simultaneously specified spatial autoregressive models, as well as autoregressions from time series, for illustration. In particular, we show that in this context the least median of squares estimator has a breakdown-point much lower than the familiar 50%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D.L. Donoho and P.J. Huber. The notion of breakdown point. In P.J. Bickel, K.A. Doksum, and J.L. Hodges, editors, A Festschrift for Erich L. Lehmann, pages 157–184. Belmont, CA, 1983.
M.G. Genton. Spatial breakdown point of variogram estimators. Mathematical Geology, 30: 853–871, 1998.
M.G. Genton. The change-of-variance function: a tool to explore the effects of dependencies in spatial statistics. J. Statist. Planning and Inf., 98:191–209, 2001.
M.G. Genton and A. Lucas. Comprehensive definitions of breakdown-points for independent and dependent observations. Tinbergen Discussion Paper TI 2000–040/2. Submitted, 2000.
F.R. Hampel. A general qualitative definition of robustness. Ann. Math. Statist.,42:1887–1896, 1971.
F.R. Hampel, E.M. Ronchetti, P.J. Rousseeuw, and W.A. Stahel. Robust statistics: The approach based on influence functions. Wiley, New York, 1986.
X. He. A local breakdown property of robust tests in linear regression. J. Multivariate Statist., 38:294–305, 1991.
X. He, D.G. Simpson, and S.L. Portnoy. Breakdown robustness of tests. J. Am. Statist. Assoc., 85:446–452, 1990.
J.L. Hodges. Efficiency in normal samples and tolerance of extreme values for some estimates of location. In Proceedings of the Fifth Berkeley Symp. Math. Statist. and Probab., volume 1, pages 163–168, 1967.
O. Hössjer. The change-of-variance function for dependent data. Probability Theory and Related Fields, 90:447–467, 1991.
H.R. Künsch. Infinitesimal robustness for autoregressive processes. Ann. Statist., 12(3): 843–863, 1984.
Y. Ma and M.G. Genton. Highly robust estimation of the autocovariance function. J. of Time Series Analysis, 21:663–684, 2000.
R.D. Martin. Robust estimation of autoregressive models. In D.R. Brillinger and G.C. Tiao, editors, Directions in Time Series, pages 228–254. Institute of Mathematical Statistics, Hayward, CA, 1980.
R.D. Martin and J. De Jong. Asymptotic properties of robust generalized M-estimates for the first-order autoregressive parameter. Technical report, Bell Laboratories Technical Memo, Murray Hill, New Jersey, 1977.
R.D. Martin and V.J. Yohai. Influence funtionals for time series. Ann. Statist., 14:781–855, 1986.
K. Ord. Estimation method for models of spatial interaction. J. Am. Statist. Assoc., 70: 120–126, 1975.
P.J. Rousseeuw. A new infinitesimal approach to robust estimation. Zeit. Wahr verw. Geb., 56:127–132, 1981.
P.J. Rousseeuw. Least median of squares regression. J. Am. Statist. Assoc., 79:871–880, 1984.
S. Sakata and H. White. An alternative definition of finite sample breakdown point with applications to regression model estimators. J. Am. Statist. Assoc., 90:1099–1106, 1995.
S. Sakata and H. White. High breakdown point conditional dispersion estimation with application to S&P 500 daily returns volatility. Econometrica, 66:529–567, 1998.
A.J. Stromberg and D. Ruppert. Breakdown in nonlinear regression. J. Am. Statist. Assoc., 87:991–997, 1992.
P. Whittle. On stationary processes in the plane. Biometrika, 41:434–449, 1954.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Genton, M.G. (2003). Breakdown-Point for Spatially and Temporally Correlated Observations. In: Dutter, R., Filzmoser, P., Gather, U., Rousseeuw, P.J. (eds) Developments in Robust Statistics. Physica, Heidelberg. https://doi.org/10.1007/978-3-642-57338-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-57338-5_12
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-642-63241-9
Online ISBN: 978-3-642-57338-5
eBook Packages: Springer Book Archive