The linear model also includes polynomial regression, in which some predictors appear in degrees equal to or greater than 2. The model continues to be linear in the parameters. For example, a second-degree parabolic regression model looks like this:
This model can easily be estimated by introducing the second-degree term in the regression model. The difference is that in polynomial regression, the equation produces a curved line, not a straight line. Polynomial regression is usually used when the relationship between the variables looks curved. A simple curve can sometimes be straightened out by transforming one or both of the variables. A more complicated curve, however, is best handled by polynomial regression.
More generally, a polynomial regression equation assumes the following form:
In the next example, we will only deal with the case of a second-degree parabolic regression in MATLAB. Now, we'll show how to model data with a polynomial. We measured the temperature...