Semiparametric and Generalized Regression Models

In the previous part of this book we found the curse of dimensionality to be one of the major problems that arises when using nonparametric multivariate regression techniques. For the practitioner, a further problem is that for more than two regressors, graphical illustration or interpretation of the results is hardly ever possible. Truly multivariate regression models are often far too flexible and general for making detailed inference.