“*C*_{pk} is calculated using an estimate of the standard deviation calculated using R-bar/d2. *P*_{pk} uses the usual form of the standard deviation ie the root of the variance or the square root of the sum of squares divided by *n – 1*. The R-bar/D2 estimation of the standard deviation has a smoothing effect and the *C*_{pk} statistic is less sensitive to points which are further away from the mean than is *P*_{pk}.”

“*C*_{pk} is calculated using RBar/d2 or SBar/c4 for Sigma in the denominator of you equation. This calculation for Sigma REQUIRES the process to be in a state of statistical control. If not in control, your calculation of Sigma (and hence Cpk) is useless – it is only valid when in-control.”

“You can have a ‘good’ *C*_{pk} yet still have data outside the specification, and the process needs to be in control before evaluating *C*_{pk}.”

Cpk is an index that is a measure of your process capability; it is a measure of meeting spec. limits and targets for your product. Cpk analysis assumes a normal distribution. First we provide a test in DfRSoft for normality to assure that the sample population is reasonably normal. According to the Central Limit Theorem we would like to see a sample size of at least 30. After normality is verified than we can use the mean and sigma values to find the Cpk Index. Most customers like to see Cpk of 1.33 or higher. Any Cpk value will also indicate a yield. This value is provided in the software and it allows the user to look at different Cpk, the associated one and two sided yields in percent and PPM. For example a Cpk of 1 has a 99.865 percent (1350 PPM) one -sided yield.