Opinion Surveys on the Euro : A Multilevel Multinomial Logistic Analysis

The main contribution of the paper is to identify the socio economic characteristics that affect the perception of the euro across the original 12 Euro Area countries by specifying and estimating a multilevel multinomial model for polytomous data. The analysis is based on the Flash Eurobarometer dataset that contains cross-country data augmented specific country macroeconomic and political series. The use of the multilevel multinomial logistic regression allows to estimate the model considering individuals features and countries characteristics in a single analysis with two-level structure. This structure takes into account dependence between individuals within the same country given a certain component of unobserved heterogeneity between countries. The attitudes towards the euro vary across individuals and across countries and are driven by personal considerations based on the benefits and costs of using a single currency within a common area. Individual features, as a high level of education and living in a metropolitan area, have a positive impact towards the perception of the euro, since people having these characteristics can benefit more from new markets opportunities created by the common area. Moreover, a positive country economic context (low inflation and high growth) can influence people attitudes