Analysis of stock market indices through multidimensional scaling

We propose a graphical method to visualize possible time-varying correlations between fifteen stock market values. The method is useful for observing stable or emerging clusters of stock markets with similar behaviour. The graphs, originated from applying multidimensional scaling techniques (MDS), may also guide the construction of multivariate econometric models.

► In this paper we: study the behaviour of fifteen stock indexes concerning the existence or emergence of clusters.
► Propose a graphical method to visualize possible time-varying correlations using MDS and dendograms.
► Observe that volatility phenomena are relevant issues in stock indices.
► Verify the different evolution of several indexes, due to the financial/economic crisis that occurred in the period under study.