Switching volatility in private international equity markets

Abstract

This paper analyzes the behavior of time‐varying volatility when structural changes are allowed in international stock markets. A model developed by Hamilton and Susmel [(1994) Autoregressive conditional heteroskedasticity and changes in regime. Journal of Econometrics 64: 307–333], the switching autoregresive conditional heteroskedastic (SWARCH) model, which is a more general specification than the popular ARCH model, is used. An exponential SWARCH model is fitted to eight series of weekly returns from international stock markets. Evidence is found for switching volatility for the US, Canada, the UK, and Japan. Under the SWARCH model, it is found that ARCH and asymmetric effects are reduced when a switching regime structure is allowed. The switching model is used to date volatility states in international stock markets. These states are compared and it is concluded that domestic volatility states tend to be independent of foreign volatility states, with the exception of Japan and the UK, and the US and Canada. For these two pairs of series, evidence is found for common volatility states. Copyright © 2000 John Wiley & Sons, Ltd.

Modelling stock return volatility dynamics in selected African markets

“…Because of the computational burden associated with the switching BEK and the resulting difficulty in obtaining convergence, this paper utilises only the MV-SWARCH model as a Markov-switching alternative to the single-state CCC-GARCH and BEK-GARCH specifications. consistent with this paper's preliminary data analysis as well as with much of the empirical literature, and is one of the features of stock market data which supports the use of conditional variance models with more than one state (Susmel, 1999).…”

Modelling stock return volatility dynamics in selected African markets

“…Because of the computational burden associated with the switching BEK and the resulting difficulty in obtaining convergence, this paper utilises only the MV-SWARCH model as a Markov-switching alternative to the single-state CCC-GARCH and BEK-GARCH specifications. consistent with this paper's preliminary data analysis as well as with much of the empirical literature, and is one of the features of stock market data which supports the use of conditional variance models with more than one state (Susmel, 1999).…”

Level-ARCH short rate models with regime switching: Bivariate modeling of US and European short rates

“…We use a Likelihood Ratio test to test the null hypothesis of independent states, cf. Susmel (2000) and Baele (2005). The test statistic is χ 2 distributed where the degrees of freedom equal the difference in the number of parameters in the restricted and unrestricted model.…”

Level-Arch Short Rate Models with Regime Switching: Bivariate Modeling of Us and European Short Rates

“…We use a Likelihood Ratio test to test the null hypothesis of independent states, cf. Susmel (2000) and Baele (forthcoming). The test statistic is χ 2 distributed where the degrees of freedom equal the difference in the number of parameters in the restricted and unrestricted model.…”

Modelling stock return volatility dynamics in selected African markets

“…Because of the computational burden associated with the switching BEK and the resulting difficulty in obtaining convergence, this paper utilises only the MV-SWARCH model as a Markov-switching alternative to the single-state CCC-GARCH and BEK-GARCH specifications. consistent with this paper's preliminary data analysis as well as with much of the empirical literature, and is one of the features of stock market data which supports the use of conditional variance models with more than one state (Susmel, 1999).…”

Level-ARCH short rate models with regime switching: Bivariate modeling of US and European short rates

“…We use a Likelihood Ratio test to test the null hypothesis of independent states, cf. Susmel (2000) and Baele (2005). The test statistic is χ 2 distributed where the degrees of freedom equal the difference in the number of parameters in the restricted and unrestricted model.…”

Level-Arch Short Rate Models with Regime Switching: Bivariate Modeling of Us and European Short Rates

“…We use a Likelihood Ratio test to test the null hypothesis of independent states, cf. Susmel (2000) and Baele (forthcoming). The test statistic is χ 2 distributed where the degrees of freedom equal the difference in the number of parameters in the restricted and unrestricted model.…”

Modelling stock return volatility dynamics in selected African markets

“…Because of the computational burden associated with the switching BEK and the resulting difficulty in obtaining convergence, this paper utilises only the MV-SWARCH model as a Markov-switching alternative to the single-state CCC-GARCH and BEK-GARCH specifications. consistent with this paper's preliminary data analysis as well as with much of the empirical literature, and is one of the features of stock market data which supports the use of conditional variance models with more than one state (Susmel, 1999).…”

Level-ARCH short rate models with regime switching: Bivariate modeling of US and European short rates

“…We use a Likelihood Ratio test to test the null hypothesis of independent states, cf. Susmel (2000) and Baele (2005). The test statistic is χ 2 distributed where the degrees of freedom equal the difference in the number of parameters in the restricted and unrestricted model.…”

Level-Arch Short Rate Models with Regime Switching: Bivariate Modeling of Us and European Short Rates

“…We use a Likelihood Ratio test to test the null hypothesis of independent states, cf. Susmel (2000) and Baele (forthcoming). The test statistic is χ 2 distributed where the degrees of freedom equal the difference in the number of parameters in the restricted and unrestricted model.…”