Determinants of sovereign ratings: A comparison of case-based reasoning and ordered probit approaches

Abstract

The paper compares two alternative techniques for the modelling of the determinants of sovereign ratings, specifically, ordered probit and case-based reasoning. Despite the differences in approach the two alternative modelling approaches produce similar results in terms of which variables are significant and forecast accuracy. This suggests that either approach can be used, and that there is some robustness in the results. As regards significant variables, both models find that a proxy for technological development, specifically, mobile phone use, is the most important variable. Apart from the technology proxy, a range of conventional macroeconomic variables are found to be significant, in particular GDP and inflation. The models are then used to produce forecasts for 2002 and for a set of unrated countries. The forecast comparison indicates the critical role played by the technology proxy variable in the modelling. JEL Codes: G15

Macroeconomics Determinants of Sovereign Credit Ratings

“…As the conclusion, the GNP per capita and inflation are the key economic indicators emphasized by the CRAs in determining the ratings. -Bheenick et al (2006) compared the results of two methods: the Case-based reasoning (CBR) and the ordered probit approach. As expected, the variable of GDP is significant across the rating of the three CRAs: the Standard & Poor"s, the Moody"s and the Fitch.…”

Short- and long-run determinants of sovereign debt credit ratings

“…These methods will themselves determine the size of the differences between each category. For example, this procedure was used by Hu et al (2002), Bissoondoyal-Bheenick (2005, Bissoondoyal-Bheenick et al (2006) and Depken et al (2007). Although this should be considered the preferred estimation procedure it is not entirely satisfying.…”

Sovereign Risk Ratings: Biased Toward Developed Countries?

“…The determinants of sovereign ratings have been a core subject in many studies (e.g., Alexe et al 2003;Bennell et al 2006;Bissoondoyal-Bheenick et al 2005;Hu et al 2002). 2 Among these, Alexe et al (2003) discussed the issue of country risk and developed a nonrecursive regression model to verify country grades and assign a rating for unrated ones.…”