Multivariate Transvariation Analysis and Currency Crises

The aim of this paper is to understand currency crises by selecting the macroeconomic\r\nfundamentals with a high predictive power, defining the latter as the variable\r\nability of discriminating between two groups of countries: the sound and the distressed.\r\nWe consider a sample of over one hundred countries which experienced a currency crash,\r\nfollowing Frankel and Rose (1996) and we apply the statistical methodology, transvariation\r\nanalysis, which measures the amount of overlap between the distributions of the\r\nsound and the distressed countries. The result of this methodology is a ranking of the\r\ngroups of variables who tend to better distinguish the two groups. In order to test the informative\r\npower of the selected indicators, we calculate the leave one out predictive error\r\nusing a transvariation based linear discriminant function. Our results seem to outperform\r\nFrankel and Rose (1996) probit analysis.