Process Variable

In general terms a process variable is one that influences the process. More narrowly, it may be used to describe the main experimental factors or the control factors for a process.

In mixture designs, the term process variables is often used to identify factors which are not part of the mixture but are to be included in the experimental design.

In most DOE software, process variables may be included in a final design by treating them as a Blocking factor or as Subsidiary factor(s). If there is a single process factor, treating it as a blocking factor will usually lead to a smaller design than treating it as a subsidiary factor. Multiple process factors used with a mixture design can be incorporated into a subsidiary design or by allocating one factor to Blocks and the remainder to a subsidiary design.

The classification of factors as a main mixing factor or as a blocking process factor or as a subsidiary process factor is for design purposes only. When the data is to analyzed, these distinctions are not operative. The analysis is only constrained by the data itself. In general, the primary constraint is that the design did not allocate runs to estimate any interactions between mixture factors and process factors. In practice the data may be able to estimate some interactions, especially if one or more factors are found to be not significant.

Learn more about the DOE tools for designed experiments in Six Sigma Demystified (2011, McGraw-Hill) by Paul Keller, in his online Intro. to DOE short course (only $99) or online Advanced Topics in DOE short course (only $139), or his online Black Belt certification training course ($875).