Authors: P L Hammer A Kogan M A Lejeune
Publish Date: 2009/04/10
Volume: 188, Issue: 1, Pages: 185-213
Abstract
The central objective of this paper is to develop a transparent consistent selfcontained and stable country risk rating model closely approximating the country risk ratings provided by Standard and Poor’s SP The model should be nonrecursive ie it should not rely on the previous years’ SP ratings The set of variables selected here includes not only economicfinancial but also political variables We propose a new model based on the novel combinatoriallogical technique of Logical Analysis of Data which derives a new rating system only from the qualitative information representing pairwise comparisons of country riskiness We also develop a method allowing to derive a rating system that has any desired level of granularity The accuracy of the proposed model’s predictions measured by its correlation coefficients with the SP ratings and confirmed by kfolding crossvalidation exceeds 95 The stability of the constructed nonrecursive model is shown in three ways by the correlation of the predictions with those of other agencies Moody’s and The Institutional Investor by predicting 1999 ratings using the nonrecursive model derived from the 1998 dataset applied to the 1999 data and by successfully predicting the ratings of several previously nonrated countries This study provides new insights on the importance of variables by supporting the necessity of including in the analysis in addition to economic variables also political variables in particular “political stability” and by identifying “financial depth and efficiency” as a new critical factor in assessing country riskPeter L Hammer tragically died in a car accident on December 27 2006 after this manuscript was essentially completed The authors express their appreciation to Dr Sorin Alexe for his invaluable help in the execution of computational experiments with LAD The authors gratefully acknowledge the partial support of the National Science Foundation Grant NSFIIS0312953 and of the National Institutes of Health Grants NIHHL07277102 and NIHDK06746802
Keywords: