ABSTRACT
As engineers we would like to make rationale trade-os with a variable we “control” (e.g., pavement thickness, font size, speed limit) in order to meet some objective (e.g., increases in pavement life, sign visibility, safety). However, we need to have a model that relates the two variables, and we must to be able to test the model for accuracy. For example, a common assumption by novices is that by reducing the speed limit, vehicle speeds
will automatically decrease. In this chapter it will be shown how a model that can be used to test this hypothesis can be developed and utilized. is chapter is focused on modeling a particular subset of all these types of relationships, or the situation where the relationship between two variables is linear in the parameters, that is, where the response of a particular variable is linear in nature (at least in the particular range of data under examination). We start this chapter using a straight-line example, and then proceed to more complicated examples.
