Bernoulli

  • Bernoulli
  • Volume 13, Number 4 (2007), 1179-1194.

The delta method for analytic functions of random operators with application to functional data

J. Cupidon, D.S. Gilliam, R. Eubank, and F. Ruymgaart

Full-text: Open access

Abstract

In this paper, the asymptotic distributions of estimators for the regularized functional canonical correlation and variates of the population are derived. The method is based on the possibility of expressing these regularized quantities as the maximum eigenvalue and the corresponding eigenfunctions of an associated pair of regularized operators, similar to the Euclidean case. The known weak convergence of the sample covariance operator, coupled with a delta-method for analytic functions of covariance operators, yields the weak convergence of the pair of associated operators. From the latter weak convergence, the limiting distributions of the canonical quantities of interest can be derived with the help of some further perturbation theory.

Article information

Source
Bernoulli, Volume 13, Number 4 (2007), 1179-1194.

Dates
First available in Project Euclid: 9 November 2007

Permanent link to this document
https://projecteuclid.org/euclid.bj/1194625607

Digital Object Identifier
doi:10.3150/07-BEJ6180

Mathematical Reviews number (MathSciNet)
MR2364231

Zentralblatt MATH identifier
1129.62011

Keywords
delta-method for analytic functions of covariance operators perturbation theory regularization of operators regularized functional canonical correlation and variates weak convergence

Citation

Cupidon, J.; Gilliam, D.S.; Eubank, R.; Ruymgaart, F. The delta method for analytic functions of random operators with application to functional data. Bernoulli 13 (2007), no. 4, 1179--1194. doi:10.3150/07-BEJ6180. https://projecteuclid.org/euclid.bj/1194625607


Export citation

References

  • Bhatia, R. (2007)., Positive Definite Matrices. Princeton: Princeton Univ. Press.
  • Bickel, P. and Levina, E. (2004). Some theory for Fisher's linear discriminant function, ``naive Bayes'', and some alternatives when there are many more variables than observations., Bernoulli 10 989--1010.
  • Chatelin, F. (1983)., Spectral Approximation of Linear Operators. New York: Academic Press.
  • Cupidon, J., Eubank, R., Gilliam, D. and Ruymgaart, F. (2006). Some properties of canonical correlations and variates in infinite dimensions., J. Multivariate Anal. To appear.
  • Dauxois, J., Pousse, A. and Romain, Y. (1982). Asymptotic theory for the principal component analysis of a vector random function: Some applications to statistical inference., J. Multivariate Anal. 12 136--154.
  • Dunford, N. and Schwartz, J.T. (1957)., Linear Operators. I. General Theory. New York: Interscience.
  • Eubank, R. and Hsing, T. (2006). Canonical correlation for stochastic processes. Technical report, Mathematics, Arizona State, Univ.
  • Gilliam. D., Hohage, T., Ji, X. and Ruymgaart, F. (2007). Fréchet-derivatives of analytic functions of compact operators and applications. Technical report, Dept. Mathematics and Statistics, Texas Tech, Univ.
  • Hastie, T., Buja, A. and Tibshirani, R. (1995). Penalized discriminant analysis., Ann. Statist. 23 73--102.
  • He, G., Müller, H.-G. and Wang, J.-L. (2004). Methods of canonical analysis for functional data., J. Statist. Plann. Inference 122 141--159.
  • Kato, T. (1966)., Perturbation Theory for Linear Operators. Berlin: Springer.
  • Kshirsagar, A. (1972)., Multivariate Analysis. New York: Dekker.
  • Laha, R.G. and Rohatgi, V.K. (1979)., Probability Theory. New York: Wiley.
  • Lax, P.D. (2000)., Functional Analysis. New York: Wiley.
  • Leurgans, S.E., Moyeed, R.A. and Silverman, B.W. (1993). Canonical correlation analysis when the data are curves., J. Roy. Statist. Soc. Ser. B 55 725--740.
  • Parzen, E. (1970). Statistical inference on time series by RKHS methods. In, Proc. Twelfth Biennial Seminar Canadian Mathematical Congress on Time Series and Stochastic Processes; Convexity and Combinatorics (R. Pyke, ed.) 1--37.
  • Rellich, F. (1969)., Perturbation Theory of Eigenvalue Problems. New York: Gordon and Breach.
  • Riesz, F. and Sz.-Nagy, B. (1990)., Functional Analysis. New York: Dover.
  • Ruymgaart, F.H. and Yang, S. (1997). Some applications of Watson's perturbation approach to random matrices., J. Multivarate Anal. 60 48--60.
  • Shin, H. (2006). Infinite dimensional discrimination and classification. Ph.D. dissertation, Texas A&M, Univ.
  • Watson, G.S. (1983)., Statistics on Spheres. New York: Wiley.