The asymptotic performance of two-sample nonparametric detectors when detecting nonfluctuating signals in non-Gaussian noise (Corresp.) | IEEE Journals & Magazine | IEEE Xplore

The asymptotic performance of two-sample nonparametric detectors when detecting nonfluctuating signals in non-Gaussian noise (Corresp.)


Abstract:

The asymptotic relative efficiencies (ARE) of generalized sign (GS), Mann-Whitney (MW), modified Savage (MS), and modified rank squared (MRS) two-sample nonparametric det...Show More

Abstract:

The asymptotic relative efficiencies (ARE) of generalized sign (GS), Mann-Whitney (MW), modified Savage (MS), and modified rank squared (MRS) two-sample nonparametric detectors are compared with those of the mean and median parametric detectors. The signal is assumed to be nonfluctuating, and the background noise is assumed to be lognormal or to be characterized by a contaminated normal distribution. It is shown that using the asymptotic relative efficiency measure the performance of nonparametric detectors increases appreciably as the noise distribution deviates from normality.
Published in: IEEE Transactions on Information Theory ( Volume: 25, Issue: 1, January 1979)
Page(s): 124 - 127
Date of Publication: 06 January 2003

ISSN Information:


References

References is not available for this document.