In any industrial process, one can enumerate causes or factors that act on one or more quality characteristics of the resulting product such that they fail to meet customers' specifications, generating items deemed as nonconforming. Modeling the fraction or proportion of nonconforming items using linear regression models is not adequate for at least two reasons: (i) proportions are assumed to follow a Normal distribution, which is not correct, and (ii) predicted responses will not necessarily be confined in the [0,1]-interval. Alternative approaches to the modeling of nonconforming proportions are based on Generalized Linear Models and Beta Regression Models. In this paper we present a case study where the objective is to model the nonconforming fraction of items emerging from a tanning process; our analysis uses Generalized Linear Models and Beta Regression Models. The developments presented in the paper may be extended to other industrial process where the proportion of nonconforming items is easily accessible.
generalized linear model; beta regression model; fraction nonconforming
