A new regularization method for regression models is proposed. The criterion to be minimized contains a penalty term which explicitly links strength of penalization to the correlation between predictors. As the elastic net, the method encourages a grouping effect where strongly correlated...

The varying-coefficient model allows to investigate and visualize the form of the interaction of variables in the predictor. Moreover, common approaches like semiparametric modeling and generalized linear models are special cases. The focus is on local estimators, in particular local likelihood...