Parameter Estimation of Continuous-Time Stationary Gaussian Processes with Rational Spectra

This paper considers the problem of estimating the parameters of continuous-time stationary Gaussian processes with rational spectra, from uniformly sampled measurements. A lower bound on unbiased estimates of the continuous-time parameters is derived. It is shown by example that this bound depends on the sampling interval in a non-monotonic manner, and that there exists a sampling interval for which the lower bound is minimized.