Six Sigma revisited: We need evidence to include a 1.5 SD shift in the extraanalytical phase of the total testing process

The Six Sigma methodology has been widely implemented in industry, healthcare, and laboratory medicine since the mid-1980s. The performance of a process is evaluated by the sigma metric (SM), and 6 sigma represents world class performance, which implies that only 3.4 or less defects (or errors) per million opportunities (DPMO) are expected to occur. However, statistically, 6 sigma corresponds to 0.002 DPMO rather than 3.4 DPMO. The reason for this difference is the introduction of a 1.5 standard deviation (SD) shift to account for the random variation of the process around its target. In contrast, a 1.5 SD shift should be taken into account for normally distributed data, such as the analytical phase of the total testing process; in practice, this shift has been included in all type of calculations related to SM including non-normally distributed data. This causes great deviation of the SM from the actual level. To ensure that the SM value accurately reflects process performance, we concluded that a 1.5 SD shift should be used where it is necessary and formally appropriate. Additionally, 1.5 SD shift should not be considered as a constant parameter automatically included in all calculations related to SM.