• Brennan, L. E., and J. D. Mallett, 1976: Efficient simulation of external noise incident on arrays. IEEE Trans. Antennas Propag.,24, 740–741.

    • Crossref
    • Export Citation
  • Courant, R., and D. Hilbert, 1966: Methods for Mathematical Physics. Vol. I. Interscience, 561 pp.

  • Garrett, C. J. R., and B. Petrie, 1981: Dynamical aspects of the flow through the Strait of Belle Isle. J. Phys. Oceanogr.,11, 376–393.

    • Crossref
    • Export Citation
  • Jenkins, G. M., and D. G. Watts, 1968: Spectral Analysis and Its Applications. Holden-Day, 525 pp.

  • Juszko, B.-A., R. F. Marsden, and S. R. Waddell, 1995: Wind stress from wave slopes using Phillips equilibrium theory. J. Phys. Oceanogr.,25, 185–203.

    • Crossref
    • Export Citation
  • Kundu, P. K., and J. S. Allen, 1976: Some three-dimensional characteristics of low frequency current fluctuations near the Oregon coast. J. Phys. Oceanogr.,6, 181–199.

    • Crossref
    • Export Citation
  • Labrecque, A. J., R. E. Thompson, M. W. Stacey, and J. R. Buckley, 1994: Residual currents in Juan de Fuca Strait. Atmos.–Ocean,32, 375–394.

    • Crossref
    • Export Citation
  • Mandel, J., 1964: The Statistical Analysis of Experimental Data. Wiley-Interscience, 410 pp.

  • Marsden, R. F., and B.-A. Juszko, 1989: Wind estimates from wave slopes. J. Geophys. Res.,94, 6266–6272.

    • Crossref
    • Export Citation
  • ——, ——, and R. G. Ingram, 1995: Internal wave directional spectra using an acoustic Doppler current profiler. J. Geophys Res.,100, 16 179–16 192.

  • Overland, J. E., and R. W. Preisendorfer, 1982: A significance test for principal components applied to a cyclone climatology. Mon. Wea. Rev.,110, 1–4.

    • Crossref
    • Export Citation
  • Savenkoff, C., A. F. Vézina, and Y. Gratton, 1997: Effect of a freshwater pulse on mesoscale circulation and phytoplankton distribution is the Lower St. Lawrence Estuary. J. Mar. Res.,55, 353–381.

    • Crossref
    • Export Citation
  • Webb, A. J., and S. Pond, 1986: A modal decomposition of the internal tide in a deep, strongly, stratified inlet: Knight Inlet, British Columbia. J. Geophys. Res.,91, 9721–9738.

    • Crossref
    • Export Citation
  • Wunsch, C., 1996: The Ocean Circulation Inverse Problem. Cambridge University Press, 442 pp.

    • Crossref
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 1 1 1
PDF Downloads 0 0 0

A Proposal for a Neutral Regression

View More View Less
  • 1 Department of Physics, Royal Military College of Canada, Kingston, Ontario, Canada
Restricted access

Abstract

In cases of modest correlation, parameters calculated from a standard least squares linear regression can vary depending on the selection of dependent and independent variates. A neutral regression that addresses this problem is proposed. The eigenvector corresponding to the smallest eigenvalue of the cross-correlation matrix of the two variates is used as a set of regression coefficients. Error bars are calculated for the eigenvalues and eigenvectors by means of a perturbation expansion of the cross-correlation matrix and are then verified by Monte Carlo simulation. A procedure is suggested for extension of the technique to the multivariate case. Examples of a linear fit for low-correlation and a quadratic fit for high-correlation cases are given. Conclusions are presented regarding the strengths and weaknesses of both the least squares and the neutral regression.

Corresponding author address: Dr. Richard F. Marsden, Physics Department, Royal Military College of Canada, P.O. Box 17000 STN FORCES, Kingston, ON K7K 7B4, Canada.

Email: marsden-r@rmc.ca

Abstract

In cases of modest correlation, parameters calculated from a standard least squares linear regression can vary depending on the selection of dependent and independent variates. A neutral regression that addresses this problem is proposed. The eigenvector corresponding to the smallest eigenvalue of the cross-correlation matrix of the two variates is used as a set of regression coefficients. Error bars are calculated for the eigenvalues and eigenvectors by means of a perturbation expansion of the cross-correlation matrix and are then verified by Monte Carlo simulation. A procedure is suggested for extension of the technique to the multivariate case. Examples of a linear fit for low-correlation and a quadratic fit for high-correlation cases are given. Conclusions are presented regarding the strengths and weaknesses of both the least squares and the neutral regression.

Corresponding author address: Dr. Richard F. Marsden, Physics Department, Royal Military College of Canada, P.O. Box 17000 STN FORCES, Kingston, ON K7K 7B4, Canada.

Email: marsden-r@rmc.ca

Save