Abstract:*

A parsimonious yet general assumption yields useful bounds for expected values of censored payoffs typically observed for option-like payoffs and credit-risk events. While most associated valuation models require available data to compute these expected values, these bounds do not. As such, the bounds are helpful to prudently gauge the risks associated with events that do not bear out in data. Examples of such risks are anticipated events not present in historical data or an illiquid market for the type of instruments usually applied in the calibration of model parameters. A number of applications stand out to conservatively value censored investment payments, prudently design model add-ons from a risk management standpoint and as alternatives to explicitly compute the expected payoff in the face of data limitations. In addition, we propose test statistic with asymptotic properties to gauge the validity of the required assumption.   

*Co-authored with Kar Yin Lam (coauthor)

General information:

This seminar will be organised in a hybrid setup. If you are interested in joining this seminar, please send an email to the secretariat of Amsterdam Business School at secbs-abs@uva.nl.