DocumentCode
871298
Title
On the Fisher information for the mean of a Gaussian process
Author
Porat, Boaz
Author_Institution
Dept. of Electr. Eng., Technion-Israel Inst. of Technol., Haifa, Israel
Volume
43
Issue
8
fYear
1995
fDate
8/1/1995 12:00:00 AM
Firstpage
2033
Lastpage
2035
Abstract
An approximate formula for the Fisher information matrix of a Gaussian process has previously been proposed, for the case of a nonzero, parametrically modeled mean. The present author shows that the relative error in the approximation is not guaranteed to converge to zero as the number of measurements tends to infinity. Therefore, the formula cannot be regarded as a valid approximation in general
Keywords
Gaussian processes; autoregressive processes; discrete systems; error analysis; function approximation; information theory; random processes; signal processing; Fisher information matrix; Gaussian process; approximate formula; relative error; Approximation error; Covariance matrix; Discrete Fourier transforms; Gaussian processes; Random processes;
fLanguage
English
Journal_Title
Signal Processing, IEEE Transactions on
Publisher
ieee
ISSN
1053-587X
Type
jour
DOI
10.1109/78.403374
Filename
403374
Link To Document