Not all associations are linear -- some may be non-linear. There is a way to test whether or not data on a scatter plot is a linear association and can be modeled by a straight line. You can do this by analyzing the residual values in a graph called the residual plot. Let's define these terms.
Residual
A residual value is the difference between the observed value and the predicted value of the dependent variable.
That is, Residual = Observed value - Predicted value
So, every data point on a scatter plot has one residual; and it indicates how far off you are from what you predicted.
Residual Plot
A residual plot is a graph that shows the residuals on the vertical axis and the independent variable on the horizontal axis.
Note: If the points in a residual plot are randomly dispersed around the horizontal axis, a linear model is appropriate for your data set. If not, a non-linear model is appropriate.
You will learn about non-linear models later on in this section. Next, take a look at how a residual plot is graphed from start to finish.
