A PROBABILISTIC MODEL FOR THE SPATIAL-DISTRIBUTION OF PARTY SUPPORT IN MULTIPARTY ELECTORATES

Spatial models of electoral competition locate voters and parties at p oints in euclidean space-representing issue positions-and specify util ity of voters for parties as functions of these positions. Utility fun ctions may also have stochastic components unassociated with issues. I n this article probabilistic models are compared in which the utility function incorporates distance between voter and party positions (prox imity model) or a scalar product (directional model). Model specificat ion is significant because of its relation to party strategy and the r esulting spatial distribution of parties. Maximum likelihood is used t o estimate parameters of a mixed directional and proximity model-with stochastic and strategic components-from data in Norwegian and Swedish election studies. Expected spatial distributions of voters by party s upport are determined for the multiparty electorates of Norway and Swe den. Unlike previous deterministic work, which strongly favors the dir ectional model, the results obtained here suggest that a mixture of pr oximity and directional probabilistic models may provide a substantial ly better fit than either pure model or a deterministic model.