Assuming a normal-Wishart modelling framework we compare two methods for finding outliers in a multivariate regression (MR) system. One method is the add-1-dummy approach which needs fewer parameters and a model choice criterion while the other method estimates the outlier probability for each...

The key element of models of contest is the Contest Success Function (CSF) which specifiesthe winning probabilities of agents. The existing axiomatizations of CSFs assume thatcontestants can make only one type of investment. This paper generalizes these axiomatizationsto the case where each...

The key element of models of contest is the Contest Success Function (CSF) whichspecifies the winning probabilities of agents. We provide an axiomatization of two parametricfamilies of CSF’s. In the first, the winning probability of each agent depends onthe investments and a vector of...