Av. Dandawate et Gb. Giannakis, ASYMPTOTIC THEORY OF MIXED TIME AVERAGES AND KTH-ORDER CYCLIC-MOMENT AND CUMULANT STATISTICS, IEEE transactions on information theory, 41(1), 1995, pp. 216-232
Citations number
40
Categorie Soggetti
Information Science & Library Science","Engineering, Eletrical & Electronic
We generalize Parzen's analysis of ''asymptotically stationary'' proce
sses to mixtures of deterministic, stationary, nonstationary, and gene
rally complex time series. Under certain mixing conditions expressed i
n terms of joint cumulant summability, we show that time averages of s
uch mixtures converge in the mean-square sense to their ensemble avera
ges. We additionally show that sample averages of arbitrary orders are
jointly complex normal and provide their covariance expressions. Thes
e conclusions provide us with statistical tools that treat random and
deterministic signals on a common framework and are helpful in definin
g generalized moments and cumulants of mixed processes. As an importan
t consequence, we develop consistent and asymptotically normal estimat
ors for time-varying, and cyclic- moments and cumulants of Kth-order c
yclostationary processes and provide computable variance expressions.
Some examples are considered to illustrate the salient features of the
analysis.