Classification of longitudinal profiles based on semi-parametric regression with mixed effects

A semi-parametric model is applied in order to model counts of letters for the federal Austrian postal system. Random coefficients are introduced into the splined variable of the semi-parametric regression model to describe heterogeneity of the temporal effect. Pfeifer and Seeber propose estimates for random coefficients to classify post offices by a hierarchical cluster algorithm. In this article, we apply two model based approaches for classification. It turns out here that both the hierarchical and the model based approach are useful for explorative cluster analysis.