For a process with stationary first differences necessary and sufficient conditions for the variance of the process to be unbounded are given. An example shows that the variance of an integrated process -- while being unbounded -- need not diverge to infinity. Sufficient conditions for the...

In this paper we apply compactly supported wavelets to the ARFIMA(p,d,q) long-memory process to develop an alternative maximum likelihood estimator of the differencing parameter, d, that is invariant to the unknown mean and model specification, and to the level of contamination. We show that...

This paper develops a consistent OLS estimate of a fractionally integrated processes' differencing parameter, using continuous wavelet theory as constructed from smoothing kernels. We show that a log-log linear relationship exists between the variance of the wavelet coefficient and the level at...

In this paper we use a bivariate, fractionally integrated, autoregressive, moving average model of money and real output to extend Fisher and Seater (1993) long-run neutrality requirements to long-memory processes. We derive new restrictions on the order of the nominal and real variable and...

This paper proposes a methodology for measuring credit booms and uses it to identify credit booms in emerging and industrial economies over the past four decades. In addition, we use event study methods to identify the key empirical regularities of credit booms in macroeconomic aggregates and...

We examine the relationships between credit default swap (CDS) premiums and bond yield spreads for nine emerging market sovereign borrowers. We find that these two measures of credit risk deviate considerably in the short run, due to factors such as liquidity and contract specifications, but we...

Models of business cycles in emerging economies explain the negative correlation between country spreads and output by modeling default risk as an exogenous interest rate on working capital. Models of strategic default explain the cyclical properties of sovereign spreads by assuming an exogenous...

In this article, we extend the conditional ICAPM of De Santis and Gérard (1997,1998) using an asymmetric multivariate GARCH specification. The model is estimated, for the period March 1973-March 2003, simultaneously for 8 markets: the world market, 4 developed markets and 3 emerging markets....

This paper contributes to the discussion on the efficiency of newly emerged financial markets in transition economies. We use data on one of the most developed financial markets in transition, the Czech Republic, to investigate financial market efficiency by examining the reaction to...

Twenty-two significant bubbles followed by large crashes or by severe corrections in the Argentinian, Brazilian, Chilean, Mexican, Peruvian, Venezuelan, Hong-Kong, Indonesian, Korean, Malaysian, Philippine and Thai stock markets indices are identified and analysed for log-periodic signatures...