CHARACTERIZATIONS OF GAUSSIAN RANDOM PROCESSES BY REPRESENTATIONS IN TERMS OF INDEPENDENT RANDOM VARIABLES,
Abstract
The report contains an investigation of certain classes of random processes having the same covariance function and some linear representations of those processes. The study considers various Gaussian and non-Gaussian models of random noise and shows that some of the most useful properties of the Gaussian model are not shared by physically reasonable non-Gaussian models. It is possible to define certain non-Gaussian processes as sums of a random number of random pulses. Necessary and sufficient conditions for the independence of linear functionals of these processes are obtained. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1969
- Accession Number
- AD0692702
Entities
People
- Percy A. Pierre
Organizations
- RAND Corporation