ABSTRACT
Quite often, experimental research work requires the empirical identification of the relationship between an observable response variable, Y, and a set of associated variables, or factors, believed to have an effect on Y. In general, such a relationship, if it exists, is unknown, but is usually assumed to be of a particular form, provided that it can adequately describe the dependence ofY on the associated variables (or factors). This results in the establishment of the so-called postulated model which contains a number of unknown parameters, in addition to a random experimental error term. The role of this error term is to account for the extra variation in Y that cannot be explained by the postulated model. In particular, if the unknown parameters appear linearly in such a model, then it is called a linear model.
