Advertisement

Statistics and Computing

, Volume 6, Issue 2, pp 93–99 | Cite as

Change-point approach to data analytic wavelet thresholding

  • Todd Ogden
  • Emanuel Parzen
Papers

Abstract

Previous proposals in data dependent wavelet threshold selection have used only the magnitudes of the wavelet coefficients in choosing a threshold for each level. Since a jump (or other unusual feature) in the underlying function results in several non-zero coefficients which are adjacent to each other, it is possible to use change-point approaches to take advantage of the information contained in the relative position of the coefficients as well as their magnitudes. The method introduced here represents an initial step in wavelet thresholding when coefficients are kept in the original order.

Keywords

nonparametric regression jump detection Brownian bridge Kolmogorov-Smirnov 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Abramovich, F. and Benjamini, Y. (1995) Thresholding of wavelet coefficients as multiple hypothesis testing procedure. In Wavelets and Statistics (A. Antoniadis and G. Oppenheim, eds.), pp. 5–14. Spriniger-Verlag, New York.Google Scholar
  2. Benjamini, Y. and Hochberg, Y. (1995) Controlling the false discovery rate: A practical and powerful approach to multiple testing. Journal of the Royal Statistical Society, Series B, 57, 289–300.Google Scholar
  3. Chui, C. K. (1992) An Introduction to Wavelets. Academic Press, New York.Google Scholar
  4. Chui, C. K. and Quak, E. (1992) Wavelets on a bounded interval. In Numerical Methods of Approximation Theory, D. Braess and L. L. Schumaker (eds.), pp. 1–31. Birkhauser-Verlag, Basel.Google Scholar
  5. Cohen, A., Daubechies, I., Jawerth, B. and Vial, P. (1993) Multi-resolution analysis, wavelets and fast algorithms on an interval. Comptes Rendus des Séances de l'Académie des Sciences, Serie I, 316, 417–21.Google Scholar
  6. Daubechies, I. (1992) Ten Lectures on Wavelets. SIAM, Philadelphia.Google Scholar
  7. Donoho, D. L. and Johnstone, I. M. (1992) Nonlinear solution for linear-inverse problems by wavelet-vaguelette decomposition. Technical report 403, Stanford University Department of Statistics, Stanford, California.Google Scholar
  8. Donoho, D. L. and Johnstone, I. M. (1994) Ideal spatial adaptation via wavelet shrinkage. Biometrika, 81, 425–55.Google Scholar
  9. Donoho, D. L. and Johnstone, I. M. (1995a) Adapting to unknown smoothness via wavelet shrinkage. Journal of the American Statistical Association, 90, 1200–24.Google Scholar
  10. Donoho, D. L. and Johnstone, I. M. (1995b) Wavelet shrinkage: Asymptopia? Journal of the Royal Statistical Society, Series B, 57, 301–69.Google Scholar
  11. Johnstone, I. M. and Silverman, B. W. (1995) Wavelet threshold estimators for data with correlated noise. Technical report, Stanford University Department of Statistics, Stanford, California.Google Scholar
  12. Meyer, Y. (1991) Ondelettes sur l'intervalle. Revista Matemática Iberoamericana, 7, 115–33.Google Scholar
  13. Nason, G. P. (1993) Wavethresh. Software package available via anonymous ftp from Statlib.Google Scholar
  14. Nason, G. P. (1994) Wavelet regression by cross-validation. Technical report 447, Stanford University Department of Statistics, Stanford, California.Google Scholar
  15. Nason, G. P. and Silverman, B. W. (1994) The discrete wavelet transform in S. Journal of Computational and Graphical Statistics, 3, 163–91.Google Scholar
  16. Ogden, R. T. and Parzen, E. (1996) Data dependent wavelet thresholding in nonparametric regression with change- point applications. In Computational Statistics and Data Analysis, to appear.Google Scholar
  17. Parzen, E. (1992) Comparison change analysis. In Nonparametric Statistics and Related Topics, A. K. Saleh (ed.), pp. 3–15. Elsevier, Amsterdam.Google Scholar
  18. Stein, C. (1981) Estimation of the mean of a multivariate normal distribution. Annals of Statistics, 10, 1135–51.Google Scholar
  19. Vidakovic, B. (1994) Nonlinear wavelet shrinkage with Bayes rules and Bayes factors. Unpublished.Google Scholar
  20. Wang, Y. (1994) Function estimation via wavelets for data withlong-range dependence. Technical report, University of Missouri Department of Statistics, Columbia, Missouri.Google Scholar
  21. Weyrich, N. and Warhola, G. T. (1994) De-noising using wavelets and cross-validation. Technical report AFIT/EN/TR/94–01, Department of Mathematics and Statistics, Air Force Institute of Technology, AFIT/ENC, 2950 P. St., Wright-Patterson Air Force Base, Ohio.Google Scholar

Copyright information

© Chapman & Hall 1996

Authors and Affiliations

  • Todd Ogden
    • 1
  • Emanuel Parzen
    • 2
  1. 1.Department of StatisticsUniversity of South CarolinaColumbiaUSA
  2. 2.Department of StatisticsTexas A&M UniversityCollege StationUSA

Personalised recommendations