Capturing Model Risk and Rating Momentum in the Estimation of Probabilities of Default and Credit Rating Migrations

Goncalo Dos Reis, Marius Pfeuffer, Greig Smith

Research output: Contribution to journalArticlepeer-review

Abstract

We discuss the estimation of rating transition probabilities in Markov and
non-Markov setups. We first estimate a continuous time Markov chain
using discrete (missing) data and derive a simpler expression for the
Fisher information matrix, reducing the computation time of Wald
confidence intervals to less than half the current standard. We provide
an efficient procedure transferring such uncertainties to the rating
migrations and probabilities of default, which is of practical use.
Supported by a full data-set, we propose a tractable and parsimonious
self-exciting marked point processes model capturing the non-Markovian
effect of rating momentum. Compared to the Markov model, the non-
Markov model yields higher probabilities of default in the investment
grades, but also lower default probabilities in some speculative grades.
This agrees with empirical observations and has clear practical
implications.
We use \emph{Moody's proprietary corporate credit ratings data set}.
Implementation available in the R package \emph{ctmcd}.
Original languageEnglish
Number of pages23
JournalQuantitative Finance
Early online date7 Apr 2020
DOIs
Publication statusE-pub ahead of print - 7 Apr 2020

Fingerprint

Dive into the research topics of 'Capturing Model Risk and Rating Momentum in the Estimation of Probabilities of Default and Credit Rating Migrations'. Together they form a unique fingerprint.

Cite this