Background: The most widely followed type of financial risk is the risk of bankruptcy. Spectacular failures like those of Enron, Parmalat, and Barings Brothers, and more recently Lehman Brothers, make eye-catching headlines. But the many other, lesser failures are frequent enough to yield a body of statistical data, one that is of great interest to investment professionals. These data have been studied by the rating agencies Standard & Poor's and Moody's, who use them to evaluate their systems of associating credit ratings (from triple-A to single-C) with bonds.
Unlike many areas of finance, studies of bankruptcy statistics and the associated credit rating migrations often use discrete mathematical tools such as Markov chains and elementary probabilistic concepts like the hazard and survival functions. Yet combining economic ideas with these statistical concepts can produce quite sophisticated statistical models.
Task: Explore the impact of the macroeconomic environment on the frequency of upgrades and downgrades of an institution's credit rating. The insights gained in this exploration will be used to construct a statistical model for rating transition probabilities. Computational tools will include statistical modeling and data-mining software.
Data Sources: Some aggregate data are publicly available from the rating agencies and from the Federal Reserve Board's database. Larger databases may be obtainable from appropriate institutions, subject to confidentiality issues.
