Technical Note—Asymptotic Properties of Mean Length Estimators for Finite Markov Queues

The mean length of a queue is normally estimated by a suitable mean of observed values. In order to determine the minimum sample size consistent with some required precision, it is necessary to know the standard error of the sample mean used. Since the observations are dependent, this standard error is usually greater than the standard error for independent observations, so that a larger sample size is required. This paper derives expressions for the standard errors of some suitable estimators in the case of finite Markov queues, and examines the efficiencies of these estimators.