Title :
Gaussian random process conditioned on its past
Author_Institution :
University of Ghent, Ghent, Belgium
fDate :
7/1/1973 12:00:00 AM
Abstract :
The statistical properties of the future of a Gaussian process when conditioned on its past are shown to be easily deduced from a minor extension of well-known formulas of optimum prediction theory. Inversely, a direct calculation of those properties leads to a derivation of the basic theorems of prediction theory.
Keywords :
Covariance matrix; Gaussian processes; Integral equations; Mean square error methods; Nonlinear filters; Prediction theory; Random processes; Statistics; Tellurium; Time factors;
Journal_Title :
Proceedings of the IEEE
DOI :
10.1109/PROC.1973.9207
