Financial reporting, Multidimensional Graphics, Bankruptcy, Predictive ability

Edward I. Altman, Commercial Bank Lending: Process, Credit Scoring, and Costs of Errors in Lending, The Journal of Financial and Quantitative Analysis, Vol. 15, No. 4, Proceedings of 15th Annual Conference of the Western Finance Association, June 19-21, 1980, San Diego, California (Nov., 1980), pp. 813-832

Variation in the composition of the defaulted debt pool and credit conditions at the time of default generate time variation in the distribution of recoveries on defaulted debt, and the related distribution of losses on portfolios of credit sensitive debt. We quantify the importance of accounting for such time variation in out-of-sample comparisons of alternative approaches to forecasting recoveries or losses given default (LGD) on defaulted bonds. Using simulations of losses on defaultable bond portfolios, we show that conditional mixture models improve forecasts of expected credit losses through capturing time variation in the recovery/LGD distribution. However, the best forecasts of instrument or firm-level recovery/LGD do not necessarily provide the best forecasts of portfolio-level losses, as the latter depend on the association between errors in the default and recovery/LGD forecasts. Our systematic comparisons of cross-sectional and intertemporal forecasting performance are enabled by a fast maximum-likelihood approach to estimating conditional mixtures of distributions.

Bond ratings are usually first assigned by rating agencies to public debt at the time of issuance and are periodically reviewed by the rating companies. If deemed warranted, changes in ratings are assigned after the review. A change in a rating reflects the agency’s assessment that the company’s credit quality has improved (upgrade) or deteriorated (downgrade). A coincident effect, in some proximity to the date of the rating change, is a change in the price of the issue. This article reports on an in-depth investigation of the expected ratings changes (drift) over time. Our analysis compares rating changes from the two major agencies, Moody’s and S&P, over the period 1970–1996. For the first time, results from several studies which have documented and analyzed these data patterns are contrasted. Depending upon which study one uses, the results and implications can be very different. We expect that the findings will have implications for such diverse practitioners as bond investors who concentrate on any or all segments of the corporate bond market, eg., high yield bond and “crossover” investors, mark-to-market analysts, and traders in the new and growing market for credit-risk-derivatives and for the many analysts who properly view that credit quality assessment involves the entire spectrum of possible outcomes, not just default. A follow-up study will analyze, in greater depth, two critical characteristics of the rating drift phenomenon. These are unexpected, as well as expected, rating migration patterns and also the implied impact on the price of the fixed income instrument.