Title :
Testing for presence of kth-rder cyclostationarity
Author :
Dandawaté, Amod V.
Author_Institution :
Dept. of Electr. Eng., Virginia Univ., Charlottesville, VA, USA
Abstract :
The presence of kth-order cyclostationarity is defined in terms of nonvanishing cyclic cumulants and polyspectra. By exploiting the asymptotic normality and consistency of kth-order sample cyclic statistics, asymptotically optimal chi 2 tests are developed to detect presence of cycles in the kth-order cyclic- cumulants and polyspectra, without assuming any specific distribution on the data. Statistical tests are derived in both time- and frequency-domain and yield consistent estimates of possible cycles present in the kth-order cyclic-statistics. Explicit algorithms for k\n\n\t\t
Keywords :
signal processing; statistical analysis; algorithms; asymptotic normality; asymptotically optimal tests; cyclic statistics; frequency-domain; kth-rder cyclostationarity; nonvanishing cyclic cumulants; performance; polyspectra; simulation results; statistical tests; time domain; Algorithm design and analysis; Array signal processing; Frequency estimation; Hydrology; Parametric statistics; Signal analysis; Signal processing algorithms; Testing; Time series analysis; Time varying systems;
Conference_Titel :
Higher-Order Statistics, 1993., IEEE Signal Processing Workshop on
Conference_Location :
South Lake Tahoe, CA, USA
Print_ISBN :
0-7803-1238-4
DOI :
10.1109/HOST.1993.264559