Estimation of the correlogram for a stationary Gaussian process by random clipping

Abstract

This paper deals with the problem of estimating the correlogram of a stationary Gaussian process with known mean and variance. An unbiased estimate using random clipping by normally distributed random variable with non-zero mean is discussed, and the variance of the estimate is compared with those of competitors. Numerical comparison is performed for AR(2) process, and it indicates that the suggested estimate is preferable in many cases.