Articles |
Robust functional estimation using the median and spherical principal components
Department of Mathematical Sciences, University of Wisconsin, P.O. Box 413, Milwaukee, Wisconsin 53201, U.S.A. gervini{at}uwm.edu
Received for publication 1 May 2007. Revision received 1 February 2008.
We present robust estimators for the mean and the principal components of a stochastic process in 
. Robustness and asymptotic properties of the estimators are studied theoretically, by simulation and by example. It is shown that the proposed estimators are generally more robust to outliers than the commonly used sample mean and principal components, although their properties depend on the spacings of the eigenvalues of the covariance function.
Key Words: Breakdown point • Influence function • Nonparametric regression • Outlier detection • Stochastic process
References
-
Ash R. B., Gardner M. F. Topics in Stochastic Processes (1975) New York: Academic Press.
Bilodeau M., Brenner D. Theory of Multivariate Statistics (1999) New York: Springer.
Boente G., Fraiman R. Comment on a paper by Locantore et al. Test (1999) 8:28–35.[Web of Science]
Cuevas A., Febrero M., Fraiman R. Robust estimation and classification for functional data via projection-based depth notions. Comput. Statist (2007) 22:481–96.[CrossRef]
Dauxois J., Pousse A., Romain Y. Asymptotic theory for the principal component analysis of a vector random function: Some applications to statistical inference. J. Multivariate Anal (1982) 12:136–54.[CrossRef]
Fraiman R., Muniz G. Trimmed means for functional data. Test (2001) 10:419–40.[CrossRef][Web of Science]
Gasser, Sroka L., Jennen-Steinmetz C. Residual variance and residual pattern in nonlinear regression. Biometrika (1986) 73:625–33.
Gervini D. Free-knot spline smoothing for functional data. J. R. Statist. Soc (2006) B 68:671–87.[CrossRef]
Gower J. C. The mediancentre. Appl. Statist (1974) 23:466–70.[CrossRef]
Hall P., Hosseini-Nasab M. On properties of functional principal components analysis. J. R. Statist. Soc (2006) B 68:109–26.[CrossRef]
Hall P., Muller H.-G., Wang J.-L. Properties of principal component methods for functional and longitudinal data analysis. Ann. Statist (2006) 34:1493–517.[CrossRef]
Kemperman J. H. B. The median of a finite measure on a Banach space. Statistical Analysis Based on the L1-norm and Related Methods (Neuchâtel, 1987)—Dodge Yadolah, ed. (1987) Amsterdam: North Holland. 217–30.
Kneip A. Comment on a paper by Locantore et al. Test (1999) 8:50–4.[Web of Science]
Locantore N., Marron J. S., Simpson D. G., Tripoli N., Zhang J. T., Cohen K. L. Robust principal components for functional data (with Discussion). Test (1999) 8:1–73.[CrossRef][Web of Science]
Lopez-Pintado S., Romo J. Depth-based inference for functional data. Comput. Statist. Data Anal (2007) 51:4957–68.[CrossRef]
Luenberger D. G. Optimization by Vector Space Methods (1969) New York: John Wiley.
Malfait N., Ramsay J. O. The historical functional linear model. Canad. J. Statist (2003) 31:115–28.[CrossRef]
Marden J. Some robust estimates of principal components. Statist. Probab. Lett (1999) 43:349–59.[CrossRef]
Maronna R. A., Martin R. D., Yohai V. J. Robust Statistics: Theory and Methods (2006) New York: John Wiley.
Ramsay J. O., Silverman B. W. Functional Data Analysis (2005) 2nd ed. New York: Springer.
Vardi Y., Zhang C.-H. The multivariate L1-median and associated data depth. Proc. Natl. Acad. Sci. USA (2000) 97:1423–6.
Yao F., Lee T. C. M. Penalized spline models for functional principal component analysis. J. R. Statist. Soc (2006) B 68:3–25.[CrossRef]
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||||