Data considerations for Automated Capability Analysis

To ensure that your results are valid, consider the following guidelines when you collect data, perform the analysis, and interpret your results.

The data should be continuous

Continuous data are measurements that may potentially take on any numeric value within a range of values along a continuous scale, including fractional or decimal values. Common examples include measurements such as length, weight, and temperature.

If you have attribute data, such as counts of defectives or defects, use Binomial Capability Analysis or Poisson Capability Analysis.

Collect enough data to obtain reliable estimates of process capability
Try to collect at least 100 total data points (subgroup size*number of subgroups), such as 25 subgroups of size 4, or 35 subgroups of size 3. If you do not collect a sufficient amount of data over a long enough period of time, the data may not accurately represent different sources of process variation and the estimates may not indicate the true capability of your process.
The process must be stable and in control
If the current process is not stable, then the capability indices cannot be reliably used to assess the future, ongoing capability of the process. If you are unsure whether your process is in control, use a control chart to evaluate process stability before you perform this analysis.
Use a method that is compatible with process knowledge
Use process knowledge to confirm the method that the analysis selects. For example, the Weibull distribution works only with positive data. Suppose that the analysis selects the Weibull distribution for a process when a sample happens to have only positive values, but you know that the process routinely produces negative values. Because the characteristics of the method are not compatible with the behavior of the process, consider other methods that fit the data well.