Analysis of Contagion in Emerging Markets
Journal of Data Science 6(2008), 601-626
26 Pages Posted: 13 Mar 2007 Last revised: 19 Oct 2013
Date Written: 2007
The spread of crises from one country to another, named “contagion”, has been one of the most debated issues in international finance in the last two decades. The presence of contagion can be detected by the increase in conditional correlation during the crisis period compared to the previous period. The paper presents a brief review of three of the most used techniques to estimate conditional correlation: exponential weighted moving average, multivariate GARCH models and factor analysis with stochastic volatility models. These methods are applied to analyze the contagion between the stock market of three major Latin American economies (Brazil, Mexico and Argentina) and two emerging markets (Malaysia and Russia) The data cover the period from 09/05/1995 to 12/30/2004, which includes several crises. In general, the three methods yielded similar results, but there is no general agreement. All the methods agreed that the contagion occurred mostly during the Asian crisis.
Keywords: Contagion, Conditional Correlation, Financial Crises
JEL Classification: C50, G10
Suggested Citation: Suggested Citation