ABSTRACT
Linear regression and its generalization, the linear model, are in very common use in statistics. For example, Jennrich (1984) wrote, “I have long been a proponent of the following unified field theory for statistics: Almost all of statistics is linear regression, and most of what is left over is non-linear re-
gression.” This is hardly surprising when we consider that linear regression focuses on estimating the first derivative of relationships between variables, that is, rates of change. The most common uses to which the linear regression model is put are
1. to enable prediction of a random variable at specific combinations of other variables;
2. to estimate the effect of one or more variables upon a random variable; and
3. to nominate a subset of variables that is most influential upon a random variable.
