An overview of the use of generalized linear models in response surface methodology

Modern applications of response surface methodology (RSM) encounter experimental situations where the traditional assumptions concerning the error distribution and the form of the fitted model are not necessarily valid. Generalized linear models (GLMs) are more suited to deal with such situations. The purpose of this article is to provide an overview of the use of GLMs in RSM, particularly in the design area as well as in the determination of optimum conditions.