Abstract not found

In this paper we conduct a systematic comparison of confidence intervals around estimated probabilities of default (PD) using several analytical approaches as well as parametric and nonparametric bootstrap methods. We do so for two different PD estimation methods, cohort and duration (intensity), with 22 years of credit ratings data. We find that the bootstrapped intervals for the duration based estimates are relatively tight when compared to either analytic or bootstrapped intervals around the less efficient cohort estimator. We show how the large differences between the point estimates and confidence intervals of these two estimators are consistent with non-Markovian migration behavior. Surprisingly, even with these relatively tight confidence intervals, it is impossible to distinguish notch-level PDs for investment grade ratings, e.g. a PDAA- from a PDA+. However, once the speculative grade barrier is crossed, we are able to distinguish quite cleanly notch-level estimated PDs. Conditioning on the state of the business cycle helps: it is easier to distinguish adjacent PDs in recessions than in expansions.

This introduction places in context the papers on credit risk modelling contained in the special issue. We explain why credit risk modelling has become such a focus of interest for practitioners and ®nancial supervisors. Even though, as we explain, the current modelling technologies have significant weaknesses, they offer the possibility of major changes in the ways banks are managed and regulated. The main impediment to greater use of these models, especially by regulators, is the difficulty involved in backtesting the risk measures they produce. We suggest some thoughts on how back-testing and other types of model assessment might be performed.

Abstract not found

Over the past decade, banks have devoted many resources to developing internal risk models for the purpose of better quantifying the risks they face and allocating economic capital. These efforts have been recognized and encouraged by bank regulators. For example, the 1997 Market Risk Amendment (MRA) to the Basel Capital Accord formally incorporates banks ’ internal, market risk models into regulatory capital calculations. That is, the regulatory capital requirements for banks ’ market risk exposures are explicitly a function of the banks ’ own value-at-risk estimates. A key component in the design and implementation of the MRA was the development of qualitative and quantitative standards that must be satisfied in order for banks ’ models to be used for regulatory capital purposes. In this paper, we examine the MRA and recent regulatory experience to draw out lessons for the design and implementation of internal models-based capital regimes for other types of risk. Note: The views expressed in this paper are those of the authors and not necessarily those of the Federal Reserve Bank of New York, the Federal Reserve Bank of San Francisco or the Federal Reserve System. I.

This paper uses Monte Carlo simulations to assess the impact of noisy input parameters on the accuracy of estimated portfolio credit risk. Assumptions about input quality are derived from the distribution of historical sample statistics commonly used in default risk modelling. The resulting estimation error in the distribution of portfolio losses is considerable. Losses that are judged to occur with a probability of 0.3 % may actually occur with a probability of 1%. The paper also shows that estimation error leads to biases in VaR estimates and significance levels of backtests. The biases can be corrected by analysing predictive distributions which average over the unknown parameter values. JEL classification: G21, C13 Key words: credit risk, estimation error, value at risk, predictive distributions.

The proposed New Accord (Basel Committee on Banking Supervision) on capital requirement allows banks to calculate the minimum capital requirement using an Internal Rating-Based approach (IRB) that relies on credit risk models. Nevertheless, no studies have been conducted on leasing credit risk. This paper focuses on credit risk modelling issues of lease portfolios. We propose specific solutions dealing with the most important peculiarities of these portfolios, including their large size, the ownership of the leased assets by the lessors and the limited availability of information about the financial situation of lessees. We estimate the probability density function of losses and VaR measures in a portfolio of 35,861 rolling stock leases issued between 1990 and 2000 by a subsidiary of a well-known European financial institution. Our main results show that leasing represents a low-risk activity, especially when time after issuance is far from the origination date of the lease. Our study should go some way towards defining a benchmark for an adequate weighting ratio for the capital requirements of leasing businesses.

Abstract: In large portfolios of small and medium-sized businesses (SME), which are highly granular, concentration risk arises from correlated defaults among groups of borrowers. Consequently, measurement of concentration risk needs to take into account borrowers’ heterogeneity. One way to proceed is to extend the standard asymptotic single factor framework by introducing additional factors of systematic risk varying between groups of borrowers. Using a generalized linear mixed model, the paper extends the standard one factor credit risk model to the multi-factor framework taking into account industry effects. The paper uses a large database containing ratings history of more than 600.000 French SME over the 1999-2008 period. Results show that the standard one factor model and the IRB regulatory formula largely fail capturing potential risk concentration. Moreover, loans to the real estate industry may be a first order determinant of concentration risk, even when considering loans to small and very small businesses.

In this paper we provide an overview of the subprime mortgage securitization process and the seven key informational frictions which arise. We discuss how market participants work to minimize these frictions and speculate on how this process broke down. We continue with a complete picture of the subprime borrower and the subprime loan, discussing both predatory borrowing and predatory lending. We present the key structural features of a typical subprime securitization, document how the rating agencies assign credit ratings to mortgagebacked securities, and outline how the agencies monitor the performance of mortgage pools over time. Throughout the paper, we draw upon the example of a mortgage pool securitized by New Century during 2006.

This paper presents preliminary findings and is being distributed to economists and other interested readers solely to stimulate discussion and elicit comments. The views expressed in the paper are those of the authors and are not necessarily reflective of views at the Federal Reserve Bank of New York or the Federal