Take a look at the charts below.
Aside from being created with two different programs, can you tell the difference between these two control charts?
Give up? Well to be fair, the answer isn’t all that clear. The same data set is repeated in both charts, and both use the same control limits.
So, what’s the big difference?
The control limits in Excel took 26 steps to accurately compute, while the control limits in the CHARTrunner Lean chart were created automatically!
Not all control limits are created equal. It is critical to look at the type of sigma used in the calculation. The method that leads to the most appropriate control limits uses the within subgroup variation to estimate the standard deviation, which is also known as the “estimated sigma.” This is the method used in CHARTrunner Lean.
In contrast, by default Excel uses an alternative method, using the standard deviation for all of the data. This method uses both within and between subgroup variation, an approach that typically leads to a larger sigma and therefore larger inappropriate control limits.
To create control limits with the correct sigma in Excel, it takes a time-consuming 26 steps each time new limits need to be calculated! With this lengthy process it’s no surprise that most users typically do not take the time to calculate the estimated sigma for control limits. Therefore, many users are unknowingly making decisions based on inappropriate data which could lead to costly out-of-control processes and increased waste.
SPC charting can be a powerful tool, when performed correctly, but as we see in the example above, there can be more than what meets the eye. It’s important to look beyond the surface of the chart and ensure the proper calculations are being used to guide business decisions. Control chart software, such as CHARTrunner Lean, that uses statistically correct calculations can help ensure your SPC charting results are always accurate.