SAS/QC Software

Process Capability Analysis

A process capability analysis compares the distribution of output from an in-control process to its specification limits to determine the consistency with which the specification limits can be met.

Two-Way Comparative Histogram with Normal Density Curves
Two-Way Comparative Histogram with Normal Density Curves

Graphical Methods

A variety of graphical methods are available to perform process capability analysis. For example, the comparative histogram in the preceding figure shows that both Supplier A and Supplier B met the specification limits better following the training program. Histograms allow you to make graphical comparisons between the distribution of the output and various theoretical distributions. You can superimpose probability density curves and specification limits, as in the figure.

You can also create cumulative distribution function plots, quantile-quantile plots, probability plots, and probability-probability plots, all of which facilitate the comparison of a data distribution with various theoretical distributions.

Statistical Methods

You can produce simple descriptive statistics in addition to quantiles, percentiles, and frequency tables. You can also produce confidence, prediction, and tolerance intervals. You can compute a number of process capability indices, and you can also perform goodness-of-fit tests for a variety of distributions. This is especially important because the assumption of normality is critical to the interpretation of capability indices.

You can also perform process capability analysis with the SQC Menu System.