Confidence Intervals for Corporate Default Rates

Abstract

Summary • This Special Comment presents confidence intervals around historical average cumulative default rates by rating category over multiple horizons. The confidence intervals are derived by “bootstrapping” (creating 10,000 hypothetical data sets from) the original data set of 11,370 corporate rating histories by sampling with replacement. • The results indicate that historical mean speculative-grade default rates are generally measured fairly precisely, with standard errors less the 10% of the estimated means. Investment-grade default rates, however, are measured much less precisely, particularly for issuers rated single A or above. Precision increases at longer horizons. (See the table below.) • Moody’s long-term ratings satisfy the Basel II criteria for effectively distinguishing relative credit risk. This is true even for “low-default portfolio” portion of the rating scale — letter ratings Aaa, Aa, and single A. The Aaa and Aa default rates are statistically differentiated at the three-year investment horizon, and the Aa and single-A default rates are differentiated at all horizons greater than one year. • Such confidence intervals measure uncertainty about long-run means. In contrast, the uncertainty about the default rate of any individual ratings cohort is much greater, as revealed by the time series variation in default rates of cohorts formed at different monthly intervals. • Although the historical variation in cohort default rates has been great, Moody’s broad letter ratings consistently rank order default risk within cohorts. For example, since 1992, no higher rated cohort has experienced a higher 5-year CDR than any lower-rated cohort formed on the same month.