Visualizing time-varying correlations across stock markets

https://doi.org/10.1016/S0927-5398(00)00009-8Get rights and content

Abstract

We propose a graphical method to visualize possible time-varying correlations between stock market returns. The method can be useful for observing stable or emerging clusters of stock markets with similar behavior. The graphs, which originate from applying multidimensional scaling techniques (MDS), may also guide the construction of multivariate econometric models. We illustrate our method for the returns and absolute returns of 13 important stock markets.

Section snippets

Introduction and motivation

In this paper we propose a basically graphical descriptive method, which can yield insights into possible similarities across stock markets. The empirical results from our method can be helpful in guiding the design of statistical models, and these can be used to test hypotheses of interest. Additionally, our method can perhaps lead to the postulation of new hypotheses.

There are economic and statistical motivations why one would obtain insights into the correlation structure of international

On MDS

MDS is a popular technique in several social sciences as it aims at representing a (m×m) proximity matrix, such as a correlation matrix, in a graphical way, see Kruskal (1964). For further reference, in our application, we consider a (13×13) matrix of estimated correlations (measured over a certain sample period). In this representation, points represent the stock markets. A small distance between two points corresponds to a high correlation between two stock markets and a large distance

Correlation between 13 stock markets

In this section, we apply the MDS method described in Section 2 to correlations of 13 selected stock markets, including two USA markets, seven European markets and four Asian markets.

Concluding remarks

In this paper, we proposed simple graphical tools to visualize time-varying correlations between stock market behavior. We illustrated our MDS-based method on returns and absolute returns of 13 stock markets. We found that throughout the years, three clusters of similarly behaving stock markets have emerged, and also that Taiwan can hardly be considered as an emerging market anymore.

There are several issues relevant for further research. A first issue concerns applying our method to alternative

Acknowledgements

We would like to thank three anonymous referees for their useful comments. A previous version of this paper was presented at the Fall Meeting of the Dutch–Flemish Classification Society (VOC), November 13, 1998. We would like to thank the participants for their helpful suggestions.

References (20)

  • G. Bekaert et al.

    Time-varying world market integration

    Journal of Finance

    (1995)
  • Bekaert, G., Harvey, C.R., Lumsdaine, R.L., 1998. Dating the integration of world equity markets, unpublished...
  • T. Bollerslev

    Modeling the coherence in short-run nominal exchange rates: a multivariate generalized ARCH approach

    Review of Economics and Statistics

    (1990)
  • I. Borg et al.

    Modern Multidimensional Scaling: Theory and Applications

    (1997)
  • A. Buja et al.

    Inequalities and positive-definite functions arising from problems in multidimensional scaling

    The Annals of Statistics

    (1994)
  • F.M.T.A. Busing et al.

    PROXSCAL: a multidimensional scaling program for individual differences scaling with constraints

  • N. Cliff

    Orthogonal rotation to congruence

    Psychometrika

    (1966)
  • J. De Leeuw et al.

    Multidimensional scaling with restrictions on the configuration

  • R.F. Engle et al.

    Common volatility in international equity markets

    Journal of Business and Economic Statistics

    (1993)
  • R.F. Engle et al.

    Asset pricing with a factor ARCH covariance structure: empirical estimates for treasury bills

    Journal of Econometrics

    (1990)
There are more references available in the full text version of this article.

Cited by (0)

View full text