Estimating the Parameters of a Spatial Voting Model with Multiattributive Random Utility Models : An Empirical Analysis of the 1990 Bundestag Election

Spatial models of voting predominate in the formalization of political decisions and they continue to be a growth industry in political science. But strict empirical applications of this theory have been rare. This article intends to fill the gap between formal and empirical models and to predict the individual voting decision in a multiparty system on the basis of the spatial model. For this reason the random utility model of discrete choice, introduced by McFadden twenty years ago, will be applied. This variant of a probabilistic approach enables us to reformulate theoretically the spatial model in terms of multiattributive stochastic decision theory and to estimate empirically so-called policy reaction functions for differentiated politcal markets with any number of parties/candidates