In this study we investigate the optimal number of independent classifications per unit produced when there are two types of classification errors: type I, where product is classified as conforming when it is not in reality, and type II, where product is classified as non-conforming when in reality it is conforming. We developed an economic model to minimize the total medium cost as a function of the classification errors and the cost of each classification. Due to the complexity of the objective function associated to the model, we used an exhaustive procedure with an upper bound of the optimal value. The procedure may be implemented easily and is available either as an Excel spreadsheet or as a macro of the statistical software Minitab.
quality; control of attributes; conformity; repeated classifications; misclassification; minimization; total medium cost
