Title :
Statistics of bicoherence
Author :
Elgar, Steve ; Guza, R.T.
Author_Institution :
Dept. of Electr. & Comput. Eng., Washington State Univ., Pullman, WA, USA
fDate :
10/1/1988 12:00:00 AM
Abstract :
Numerical simulations are used to investigate statistics of biocoherence for the special case of a linear random process. Smoothed bicoherence statistics are shown to be independent of both the normalization used to form the bicoherence and of whether statistical stability is obtained by ensemble-averaging short records, or frequency merging within a long record
Keywords :
random processes; signal processing; statistical analysis; bicoherence; ensemble-averaging short records; frequency merging; linear random process; normalisation; statistical stability; Distributed power generation; Frequency estimation; Gaussian processes; Merging; Numerical simulation; Random processes; Smoothing methods; Stability; Statistical distributions; Statistics;
Journal_Title :
Acoustics, Speech and Signal Processing, IEEE Transactions on
