You have watched at break-even calculations scatter plots for estimating demand information and trends in revenue. In each of these you basic the analysis to a straight line. This is useful however sometimes these data are more complex. They may be a curved line or in its place of there being only one item for the slope, such as with variable costs there may be several factors involved in the estimate. Demand for instance may be based on price, convenience or quality. How does a linear regression permit you to better estimate trends, costs and other factors in complex situations?