Advertisement

Ukrainian Mathematical Journal

, Volume 56, Issue 8, pp 1308–1330 | Cite as

Correction of nonlinear orthogonal regression estimator

  • I. Fazekas
  • A. Kukush
  • S. Zwanzig
Article

Abstract

For any nonlinear regression function, it is shown that the orthogonal regression procedure delivers an inconsistent estimator. A new technical approach to the proof of inconsistency based on the implicit-function theorem is presented. For small measurement errors, the leading term of the asymptotic expansion of the estimator is derived. We construct a corrected estimator, which has a smaller asymptotic deviation for small measurement errors.

Keywords

Measurement Error Asymptotic Expansion Nonlinear Regression Regression Function Regression Procedure 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

REFERENCES

  1. 1.
    P. T. Boggs, H. R. Byrd, and R. B. Schnabel, “A stable and efficient algorithm for nonlinear orthogonal distance regression,” SIAM J. Sci. Comput., 8, No.6, 1052–1078 (1987).Google Scholar
  2. 2.
    H. Schwetlick and V. Tiller, “Numerical methods for estimating parameters in nonlinear models with errors in variables,” Technometrics, 27, No.1, 17–24 (1985).Google Scholar
  3. 3.
    P. T. Boggs and J. E. Rogers, “Orthogonal distance estimators,” Contemp. Math., 112, 183–194 (1990).Google Scholar
  4. 4.
    R. Strebel, D. Sourlier, and W. Gander, “A comparison of orthogonal least squares fitting in coordinate meteorology,” in: Recent Adv. Total Least Squares Techn. and Errors-in-Variables Modeling (Leuven, 1996), SIAM, Philadelphia (1997), pp. 249–258.Google Scholar
  5. 5.
    R. L. Branham, “Total least squares in astronomy,” in: Recent Adv. Total Least Squares Techn. and Errors-in-Variables Modeling (Leuven, 1996), SIAM, Philadelphia (1997), pp. 371–380.Google Scholar
  6. 6.
    W. H. Jefferys, “Robust estimation when more than one variable per equation of condition has error,” Biometrika, 77, No.3, 597–607 (1990).Google Scholar
  7. 7.
    S. van Huffel, “TLS applications in biometrical signal processing,” in: Recent Adv. Total Least Squares Techn. and Errors-in-Variables Modeling (Leuven, 1996), SIAM, Philadelphia (1997), pp. 307–318.Google Scholar
  8. 8.
    M. K. Mallick, “Applications of nonlinear orthogonal distance regression in 3D Motion estimation,” in: Recent Adv. Total Least Squares Techn. and Errors-in-Variables Modeling (Leuven, 1996), SIAM, Philadelphia (1997), pp. 273–284.Google Scholar
  9. 9.
    W. A. Fuller, Measurement Errors Models, Wiley, New York (1987).Google Scholar
  10. 10.
    S. Zwanzig, Estimation in Nonlinear Functional Errors-in-Variables Models, Habilitation, Univ. Hamburg (1998).Google Scholar
  11. 11.
    K. M. Wolter and W. A. Fuller, “Estimation of nonlinear errors-in-variables models,” Ann. Statist., 10, No.2, 539–548 (1982).Google Scholar
  12. 12.
    L. A. Stefanski, “The effect of measurement error on parameter estimation,” Biometrika, 72, No.3, 583–592 (1985).Google Scholar
  13. 13.
    L. A. Stefanski and R. J. Carroll, “Covariate measurement error in logistic regression,” Ann. Statist., 13, No.4, 1335–1351 (1985).Google Scholar
  14. 14.
    N. J. D. Nagelkerke, “Maximum likelihood estimation of functional relationship,” in: Lect. Notes Statist., 69 (1992).Google Scholar
  15. 15.
    B. Armstrong, “Measurement error in the generalized linear model,” Commun. Statist.-Simula. Computa, 14, No.3, 529–544 (1985).Google Scholar
  16. 16.
    D. W. Schafer, “Covariate measurement error in generalized linear models,” Boimetrika, 72, No.3, 583–592 (1987).Google Scholar
  17. 17.
    L. T. M. E. Hillegers, The Estimation in Functional Relationship Models, Proefschrift, Techn. Univ., Eindhoven (1986).Google Scholar
  18. 18.
    Y. Amemiya, “Generalization of the TLS approach in the errors-in-variables problem,” in: Recent Adv. Total Least Squares Techn. and Errors-in-Variables Modeling (Leuven, 1996), SIAM, Philadelphia (1997), pp. 77–86.Google Scholar
  19. 19.
    L. J. Gleser, “Some new approaches to estimation in linear and nonlinear errors-in-variables regression models,” in: Recent Adv. Total Least Squares Techn. and Errors-in-Variables Modeling (Leuven, 1996), SIAM, Philadelphia (1997), pp. 69–76.Google Scholar
  20. 20.
    A. G. Kukush and S. Zwanzig, “On the adaptive minimum contrast estimator in a model with nonlinear functional relations,” Ukr. Mat. Zh., 53, No.9, 1204–1209 (2001).Google Scholar
  21. 21.
    R. J. Carroll, C. H. Spiegelman, G. K. K. Lan, K. T. Bailey, and R. D. Abbott, “On errors-in-variables for binary regression models,” Biometrika, 71, No.1, 1925–1984 (1984).Google Scholar
  22. 22.
    L. A. Stefanski, “Correcting data for measurement errors in generalized linear models,” Commun. Statist. Theory Meth., 18, No.5, 1715–1733 (1989).Google Scholar
  23. 23.
    Y. Amemiya and W. F. Fuller, “Estimation for the nonlinear functional relationship,” Ann. Statist., 16, No.1, 147–160 (1988).Google Scholar
  24. 24.
    I. Fazekas, A. G. Kukush, and S. Zwanzig, On Inconsistency of the Least Squares Estimator in Nonlinear Functional Relations, Preprint No. 1, Odense Univ., Denmark (1998).Google Scholar

Copyright information

© Springer Science+Business Media, Inc. 2004

Authors and Affiliations

  • I. Fazekas
    • 1
  • A. Kukush
    • 2
  • S. Zwanzig
    • 3
  1. 1.Institute of InformaticsUniversity of DebrecenDebrecenHungary
  2. 2.Shevchenko Kyiv UniversityKyiv
  3. 3.Uppsala UniversityUppsalaSweden

Personalised recommendations