Multivariate conditional heteroscedasticity models with dynamic correlations for testing contagion

• Autores: Sivagowry Sriananthakumar, Param Silvapulle
• Localización: Applied financial economics, ISSN 0960-3107, Vol. 18, Nº. 4-6, 2008, págs. 267-273
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • This paper models dynamic correlations between the Asian stock market returns and studies their behaviour over the period before, during and after the Asian financial crisis, which occurred in the 1990s. To establish the presence of contagion effect, this paper investigates whether or not there is a break-down in the correlation data generating process, particularly, during crises. The East Asian block-Thai, Malaysian, Indonesian and Korean-countries stock markets were considered in this study. Using multivariate generalised autoregressive conditional heteroscedasticity (MGARCH) models with dynamic correlations, this study finds strong evidence of contagion effects between (Thailand and Malaysia), (Thailand and Korea), (Malaysia and Korea) and (Korea and Indonesia).