SAMPLING ERROR IN MEASURING THE LOAD ON A GROUP OF TELEPHONE CIRCUITS

In sampling to determine the load on a group of telephone circuits, there are two sources of variability: genuine variation in the process and errors due to sampling. The results in this paper allow the sampling error to be assessed separately from the genuine variation, so that the contributions of the two sources of variability can be identified. This allows the interval between samples to be chosen to reduce the sampling error to an acceptable level without wasteful oversampling. In this paper, general results for continuous processes are applied to the measurement of load. The form of the results is particularly simple and clearly illustrates the need for a careful approach to estimating sampling error in this context.