In this paper the statistical performance of a Variable Sampling Interval (VSI) R Exponentially Weighted Moving Average (EWMA) control chart designed to monitor the range R of samples extracted out from a normally distributed population is investigated. For the investigated chart, the sampling interval can assume two different values. A statistically optimal design strategy based on the average time to signal the occurrence of an out-of-control condition is presented and the statistical performance of the VSI R EWMA chart is assessed through a comparison with other control charts used to monitor the process dispersion. The obtained results show how the possibility of varying the sampling interval significantly improves the performance of the VSI R EWMA chart with respect to the corresponding static chart and how this kind of chart is particularly suitable when reduction in the process dispersion should be detected.