Although control charts have had a tremendous impact on quality improvement, their inability to precisely measure performance has hindered their full potential of functional performance. Measures of performance are presented for traditional 'three-sigma' charts and for X̄ charts which incorporate four rules. 'Three-sigma' charts are evaluated for power at a single subgroup, as well as for cumulative power over m subgroups. Power of X̄ charts that employ four rules is formulated on the single-subgroup level using a rule dependency approach and is compared to the operational characteristics of 'three-sigma' charts. Applications of these models to simulated data demonstrate their accuracy of power prediction. In addition, a diagnostic methodology is described which utilizes the derived performance measures to predict the mean and variance of a shifted distribution.