Quantile Forecasting for Credit Risk Management using possibly Mis-specified Hidden Markov Models

Arbeitspapier

Recent models for credit risk management make use of Hidden Markov Models (HMMs). The HMMs are used to forecast quantiles of corporate default rates. Little research has been done on the quality of such forecasts if the underlying HMM is potentially mis-specified. In this paper, we focus on mis-specification in the dynamics and the dimension of the HMM. We consider both discrete and continuous state HMMs. The differences are substantial. Underestimating the number of discrete states has an economically significant impact on forecast quality. Generally speaking, discrete models underestimate the high-quantile default rate forecasts. Continuous state HMMs, however, vastly overestimate high quantiles if the true HMM has a discrete state space. In the reverse setting, the biases are much smaller, though still substantial in economic terms. We illustrate the empirical differences using U.S. default data.

Angaben zum Objekt

• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Series: Tinbergen Institute Discussion Paper ; No. 07-046/2

Klassifikation und Themen

• Klassifikation: Wirtschaft ; Forecasting Models; Simulation Methods ; Single Equation Models; Single Variables: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes ; Financing Policy; Financial Risk and Risk Management; Capital and Ownership Structure; Value of Firms; Goodwill
• Thema: defaults ; Markov switching ; misspecification ; quantile forecast ; Expectation-Maximization ; simulated maximum likelihood ; importance sampling ; Kreditrisiko ; Risikomanagement ; Markovscher Prozess ; Modellierung ; Maximum-Likelihood-Methode ; Schätztheorie

Beteiligte, Orts- und Zeitangaben

• Ereignis: Geistige Schöpfung
• (wer): Banachewicz, Konrad ; Lucas, André
• Ereignis: Veröffentlichung
• (wer): Tinbergen Institute
• (wo): Amsterdam and Rotterdam
• (wann): 2007

Weitere Informationen

• Handle: http://hdl.handle.net/10419/86275
• Letzte Aktualisierung: 10.03.2025, 11:42 MEZ