A Non-Recursive Regression Model For Country Risk Rating

DefaultRisk.com the web's biggest credit risk modeling resource.

Submit Your Paper

Post Your Résumé

For Recruiters

Amazon.com Widgets

A Non-Recursive Regression Model For Country Risk Rating

by Sorin Alexe of Rutgers University,
Peter L. Hammer of Rutgers University,
Alexandr Kogan of Rutgers University, and
Miguel A. Lejeune of FORTIS Bank

March 2003

Abstract: The central objective of this paper is to develop a transparent, consistent, self contained, and stable country risk rating system, closely approximating one of the major existing ones (Standard & Poor's). The proposed model uses economic-financial and political variables, is non-recursive (i.e., it does not rely on the previous year's ratings) and is constructed using multiple regression. The accuracy of the linear regression's predictions measured by their correlation coefficient with Standard and Poor's ratings, evaluated by k-folding cross-validation, is 95.6%. The stability of the constructed non-recursive regression model is shown in three ways: by the correlation of the prediction with those of other agencies (Moody's and The Institutional Investor), by predicting 1999 ratings using the non-recursive multiple regression model derived from the 1998 dataset applied to the 1999 data, and by successfully predicting the ratings of several previously non-rated countries.

Keywords: Sovereign risk rating, country risk, non-recursivity, validation.

Books Referenced in this Paper: (what is this?)