Process Capability

System Model > Statistical Process Control (SPC) > Process Capability

A process is said to be capable when the percentage of samples outside the specification limits is less than a predefined value. The following assumptions need to also be true:

The process is statistically stable (only common causes of variation exist)
The individual measurements conform to a normal distributionAlso known as a `bell' curve, the normal distribution is the best known and widely applicable distribution. The distribution is symmetrical and popularly represents the laws of chance. 68.27% of the area lies between -1 sigma and +1 sigma, 95.45% between -2 sigma and+2 sigma, and 99.73% between -3 sigma and +3 sigma. The values of skewness and kurtosis are used to provide quantitative measures for normality. Assuming that at least 20 samples are used to construct a distribution, a good rule of thumb is to accept the data as a normal distribution when, -1.0 = skewness = 1.0 2 = kurtosis = 4.
Measurement variation (due to the measuring instrument) is small

The specification limits are a reflection of the customers requirements and are selectable. The percentage of samples that need to lie within the specification limits is calculated from the standard deviation (sigma)"3-sigmas" on either side of the mean.

Note: The "3-sigma" term refers to the boundaries which are located 3 standard deviations on either side of the center. For a normal distribution 99.74% of the samples are expected to fall within this boundary.

Ultimately capability determines whether the process is statistically able to meet the specification or not. Reducing the effects of common variation will make your process more capable, as shown here: