The cluster analysis methods are used in order to perform a comparative study of 15 EU countries in relation with the fluctuations of some basic macroeconomic indicators. The statistical distances between countries are calculated for various moving time windows, and the time variation of the mean statistical distance is investigated. The decreasing of the mean statistical distance between EU countries is reflected in the correlated fluctuations of the basic ME indicators: GDP, GDP/capita, Consumption and Investments. This empirical evidence can be seen as an economic aspect of globalization. The Moving Average Minimal Length Path (MAMLP) algorithm allows to search for a cluster-like structures derived both from the hierarchical organization of countries and from their relative movement inside the hierarchy. It is found that the strongly correlated countries with respect to GDP fluctuations can be partitioned into stable clusters. Some of the highly correlated countries, with respect to GDP fluctuations, display strong correlations also in the Final Consumption Expenditure, while others are strongly correlated in Gross Capital Formation. On the other hand, one notices the similitude of the classifications regarding GDP and Net Exports fluctuations as concerns the squared sum of the correlation coefficients (so called country sensitivity). The final structure proves to be robust against the constant size time window moving over the scanned time interval. The policy implications of the above empirical results concern the economic clusters arising in the presence of Marshallian externalities and the relationships between trade barriers, R&D incentives and growth that must be accounted in elaborating a cluster-promotion policy.