1.9 Regressions

There is a procedure and a formula to calculate the equation of a line of best fit.

The procedure: the line of best fit will have some points above and some points below. The vertical distance from a point to where the line of best will be is called a residual. If the point is above the line, the residual is positive and if the point is below then the residual is negative. Our goal is to minimize the squares of the residuals.

GSP demo!

The formula to calculate the least squares regression is

This formula will eventually give you an equation in the form , which is what you need to define your line of best fit.

Now that you know both methods, let’s do this the easy way.

p. 585 enter the set of data and do a linear regression

Interpolation/Extrapolation

The main purpose of a line of best fit is to predict where data is likely to be that is inside or outside of the main scatter plot but not indicated by a specific point.

When extrapolating, care must be taken to insure that the results make sense.

p.588#1-8