Nonparametric detection using spectral data

  title={Nonparametric detection using spectral data},
  author={Melvin N. Woinsky},
  journal={IEEE Trans. Information Theory},
A detection system is considered that analyzes the spectrum of the time-series output from a sensing element. The spectral data consist of a matrix of estimates of the energy in many small time-frequency cells. A decision procedure is formulated that is based on the multiple use of a two-sample statistic operating on the columns of the matrix. If the input noise is Gaussian with unknown power, the asymptotically optimum statistic t is a ratio of two sample means. Since in certain applications… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 10 references

Multiple decision procedures based on ranks for certain problems in analysis of variances,

  • M. L. Puri, P. S. Puri
  • Ann. Math. Statist.,
  • 1969

A composi te nonparametr ic test for a scale sl ippage alternattve An efficient nonparametr ic detector based on a threesample classification model

  • J. B. Thomas
  • IEEE Trans . Inform . Theory
  • 1968

Woinsky, “A composi te nonparametr ic test for a scale sl ippage alternattve,

  • M N.
  • Ann. Math. Statist.,
  • 1968

Asymptotic efficiency of certain locally most powerful rank tests

  • J. Capon
  • ZEEE Trans
  • 1967

Rank order procedures for selecting a subset containing the populat ion with the smallest scale parameter,

  • S. Blumenthal, D. W. Patterson
  • Handbook of Nonparametric Statistics,
  • 1965

The Measurement of Power Spectra From the Point of View of Communicat ions Engineering

  • R. B. Blackman, J. W. Tukey
  • New York: Dover,
  • 1959

Asymptotic normality and efficiency of certain nonparametr ic test statistics,

  • H. Chernoff, I. R. Savage
  • Ann. Math. Statist.,
  • 1958

Similar Papers

Loading similar papers…