Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1151662 | Statistics & Probability Letters | 2014 | 5 Pages |
Abstract
Let {X(t),t∈Z}{X(t),t∈Z} be a stationary time series with a.e. positive spectrum. Two consequences of that the bispectrum of {X(t),t∈Z}{X(t),t∈Z} is real-valued but nonzero are: (1) if {X(t),t∈Z}{X(t),t∈Z} is also linear, then it is reversible; (2) {X(t),t∈Z}{X(t),t∈Z} cannot be causal linear. A corollary of the first statement: if {X(t),t∈Z}{X(t),t∈Z} is linear, and the skewness of X(0)X(0) is nonzero, then third order reversibility implies reversibility. In this paper the notion of bispectrum is of a broader scope since we do not assume the absolute summability of the third order cumulants.
Related Topics
Physical Sciences and Engineering
Mathematics
Statistics and Probability
Authors
E. Iglói, Gy. Terdik,