Performance of Discrete-Time Predictors of Continuous-Time Stationary Processes.
Abstract
This document studies the asymptotic performance of linear predictors of continuous-time stationary processes from observations at n sampling instants on a fixed observation interval. Considered are both optimal and simpler choices of predictor coefficients; uniform sampling, as well as nonuniform sampling tailored to the statistics of the process under prediction. The authors concentrate on stationary processes with rational spectral densities and obtain the asymptotic performance for cases with no and with one quadratic-mean derivative. The analytical results are supplemented by numerical examples depicting small and large sample size performance. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 1985
- Accession Number
- ADA166231
Entities
People
- Elias Masry
- Stamatis Cambanis
Organizations
- University of North Carolina at Chapel Hill