Title :
Asymptotic properties and covariance expressions of kth-order sample moments and cumulants
Author :
Dandawate, Amod V. ; Giannakis, Georgios B.
Author_Institution :
Dept. of Electr. Eng., Virginia Univ., Charlottesville, VA, USA
Abstract :
Consistency and asymptotic normality of kth-order sample moments and cumulants of stationary processes is established. Further, asymptotic covariance expressions along with their computable forms are derived and special cases for k=2, 3 and 4 are explicitly discussed. This analysis generalizes the results of Bartlett and provides tools for performance evaluation and comparison of algorithms based on sample moments and cumulants. Simulations verify the given covariance expressions
Keywords :
matrix algebra; parameter estimation; signal processing; statistical analysis; algorithms; asymptotic covariance expressions; asymptotic normality; asymptotic properties; consistency; kth-order cumulants; kth-order sample moments; performance evaluation; sample moments; signal processing; simulations; stationary processes; Additive noise; Algorithm design and analysis; Computational modeling; Ear; Gaussian noise; Higher order statistics; Kernel; Performance analysis; Signal generators; Signal processing; Statistical distributions;
Conference_Titel :
Signals, Systems and Computers, 1993. 1993 Conference Record of The Twenty-Seventh Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-4120-7
DOI :
10.1109/ACSSC.1993.342384
