Ordered response models for sovereign debt ratings†

†The opinions expressed herein are those of the authors and do not necessarily reflect those of the ECB or the Eurosystem.

Abstract

Using ordered logit and probit plus random effects ordered probit approaches, we study the determinants of sovereign debt ratings. We found that the last procedure is the best for panel data as it takes into account the additional cross-section error.

Acknowledgements

Pedro Gomes would like to thank the Fiscal Policies Division of the ECB for its hospitality, and acknowledges the financial support of the FCT (Fundação para a Ciência e a Tecnologia, Portugal). UECE is also supported by the FCT.

Notes

†The opinions expressed herein are those of the authors and do not necessarily reflect those of the ECB or the Eurosystem.

¹ By estimating this specification one can interpret β as the short-run impact of the variable on the rating, while (β + η) gives the long-run effect of a change in the variable on the rating.

² We grouped the ratings in 17 categories, by assigning linearly a value of 17 to the best rating, AAA, a value of 2 to B- and a value of 1 to all observations below B-. If we used a specific number for each existing rating notch, it might be hard to efficiently estimate the threshold points between CCC +  and CCC, CCC and CCC −  and so on, given that the bottom rating categories have very few observations.