The concept of process capability was mentioned briefly in Section 4.1. What is process capability and how is it measured? Process capability generally refers to whether an in-control process is functioning in such a manner that one or more of the variables being measured have distributions that lie almost completely within the specification limits, with the latter frequently determined from engineering tolerances and/or from customers' needs. A “capable” process is one for which the distributions of the process characteristics do lie almost entirely within the engineering tolerances. Numerical measures of capability are obviously needed and are presented in this chapter.
Much attention has been devoted to process capability indices in recent years, with some writers suggesting that they not be used (Nelson, 1992; Pignatiello and Ramberg, 1993), while many researchers have concurrently worked at developing new indices.
Despite various admonitions regardless the use and interpretation of process capability indices, it is highly probable that they will continue to be used because of their simplicity. (It is this simplicity that causes problems, however, as we will see later in the chapter.)
There are essentially two phases involved in a process capability study: (1) determining how the data are to be collected and then collecting the data, and (2) selecting one or more indices and performing the computations.