We propose a computer intensive method for linear dimension reduction which minimizes the classification error directly. Simulated annealing (Bohachevsky et al 1986) as a modern optimization technique is used to solve this problem effectively. This approach easily allows to incorporate user...

We propose multivariate classification as a statistical tool to describe business cycles. These cycles are often analyzed as a univariate phenomenon in terms of GNP or industrial net production ignoring additional information in other economic variables. Multivariate classification overcomes...

For the design of most multivariate control charts, it is assumed that the observations follow a multivariate normal distribution. In practice, this assumption is rarely satisfied. In this work, a distribution-free EWMA control chart for multivariate processes is proposed. This chart is based on...

In order to replace the univariate indicators standard in the literature (cp. [Opp96]) by a multivariate representation of business cycles, the relevant 'stylized facts' are to be identified which optimally characterize the development of business cycle phases. Based on statistical...

In this paper a projection pursuit method is developed which determines optimal multivariate latent factor models based on a flexible loss function. This way, the unknown model coefficients are estimated with respect to optimal predictive power. The specification of the loss function in...