Marlene Müller
--------------
The talk introduces semiparametric extensions of the generalized
linear model. One particular model of interest is the generalized 
partial linear model (GPLM) which allows a nonparametric modelling 
of the influence of continuous covariables. Different estimation 
algorithms are discussed together with tests on the correct 
specification of this model (vs. a parametric generalized linear model). 
A special focus of this talk is on the implementation and visualization
of the GPLM. The application to a data set on credit scoring illustrates 
the use of this model.