Is there an identity within international stock market volatilities?

Previous studies have investigated the comovements of international equity returns by using mean correlations, cointegration, common factor analysis, and other approaches. This paper investigates the evolution of the affinity among major euro and non-euro area stock markets in the period 1966-2006 by using distance-based methods for clustering analysis of time series. A periodogram-based metric for mean and squared returns is used to compute distances between the series. This method solves the shortcoming of unequal sample sizes found for different countries. Then, by using dendrogram and multidimensional scaling techniques based on the computed distances, we display clusters for the series of returns and volatilities. The data were divided into two sample periods: previous and subsequent to the introduction of the euro as an electronic currency. For market returns, euro-area countries do not seem to come closer after the introduction of the euro. There is some identity that is maintained after 1998. For squared returns, we found a clear change with the introduction of the euro. Up to 1998, there is a weak linkage among euro area countries. After 1998, the euro area stock markets volatilities have become considerably more homogenous. For reference, we explored also the correlations among the series. We found that some stock markets within the European Monetary Union are strongly correlated in returns and in squared returns, and that some euro and non-euro area markets are not correlated in returns, but are weakly correlated in squared returns.