Please do not quote without permission * Chidambaran is visiting at NYU, on leave from Tulane. Lee holds joint appointments at Tulane and HKUST. Trigueros is at Tulane. We are grateful for the comments from participants at seminars at Tulane

A number of studies investigate whether various stochastic variables explain changes in return volatility by specifying the variables as covariates in a GARCH(1, 1) or EGARCH(1, 1) model. The authors show that these models impose an implicit constraint that can obscure the true role of the covariates in the analysis. They illustrate the problem by reconsidering the role of contemporaneous trading volume in explaining ARCH effects in daily stock returns. Once the constraint imposed in earlier research is relaxed, it is found that specifying volume as a covariate does little to diminish the importance of lagged squared returns in capturing the dynamics of volatility. © 2008 Wiley Periodicals, Inc. Jrl Fut Mark

This paper enhances the investigation of international linkages in stock markets by focusing on the information dependence between the markets. This is achieved by examining the causality in the variances of the stock returns from the seven members of the OECD group of countries. The characteristics of the monthly stock market return from these countries are first captured in a Markov switching framework. The approach allows both the mean and the variance to depend on an unobserved state that is driven by a Markov process. The results show that the low variance states are quite stable whereas the high variance states are shortlived. The causality test is next carried out with the estimated variance series using a recent econometric method that is robust to distributional assumption. Although the results show the dominance of the two largest economies, feedback effects are also noticed. The existence of this reverse causality has not been documented by most prior studies in this area.

The purpose of this paper is to compare the different estimation methods of Value-at-Risk (VaR) as a market risk measurement of actual bank non-linear portfolios (specifically comprised of currency options) in the context of the supervision of bank solvency. The aim is to establish the best method given these specific circumstances. The main conclusion is that, when estimating VaR for non-linear actual portfolios, in a context of supervision of bank solvency, the precision of the Monte Carlo simulation method is to be preferred to the speed that can be obtained with the variance-covariance matrix analytic method. We obtain for it, theoretical evidence as well as an empirical one. The originality of the empirical study consists in using for it a non-linear actual portfolio: the currency options portfolio of one of the biggest Spanish banks, and dated the 21st