pcme.paperex {pcme} | R Documentation |
Periodic autocovariances used in the referenced paper and in the examples in thispackage for illustration of maximum entropy completion.
data(pcme.paperex)
A list of five 4 x 2 matrices, each (possibly) representing periodic autocovariances of a periodically correlated time series with period T=2. The "possibly" qualifier is used because it may not be possible to complete these to complete periodic autocovariance sequences.
The ordering is the season-lag ordering used for all function in
package pcme
. Let
R_k(l)=Cov(X(k),X(k-l)) for k=1,2
and l=0,1,2,3. Then the arrangement of the autocorrelations in
each matrix is as follows:
R_1(0) | R_1(1) | R_1(2) | R_1(3) |
R_2(0) | R_2(1) | R_2(2) | R_2(3) |
~~ reference to a publication or URL from which the data were obtained ~~
Boshnakov, Georgi and Lambert-Lacroix, Sophie (2009?) Maximum entropy for periodically correlated processes from nonconsecutive autocovariance coefficients. Journal of Time Series Analysis (to appear)
Lambert-Lacroix, Sophie (2005) Extension of autocovariance coefficients sequence for periodically correlated processes. Journal of Time Series Analysis, 26, No. 6, 423-435.
data(pcme.paperex) names(pcme.paperex) pcme.paperex$rex1