8 Nonlinear Regression Functions
Until now we assumed the regression function to be linear, i.e., we have treated the slope parameter of the regression function as a constant. This implies that the effect on \(Y\) of a one unit change in \(X\) does not depend on the level of \(X\). If, however, the effect of a change in \(X\) on \(Y\) does depend on the value of \(X\), we should use a nonlinear regression function.
Just like for the previous chapter, the packages AER (Christian Kleiber and Zeileis 2020) and stargazer (Hlavac 2018) are required for reproduction of the code presented in this chapter. Check whether the code chunk below executes without any error messages.