Fall 2009 Thursday, October 29   Speaker: Nariankadu D. Shyamalkumar Ph.D. Assistant Professor The University of Iowa Title: On Nonparametric Estimation of the CTE Abstract: Insurance regulation in the US is undergoing a transformation with formulaic prescriptions for reserve and capital being replaced by ones requiring stochastic simulation. For example, such reserving standards for variable annuities has been adopted by the National Association of Insurance Commissioners (NAIC), and will be implemented at the end of this calendar year. The measure of risk chosen for these regulations is the Conditional Tail Expectation (CTE) of the loss variable, which at the 95% level is defined as the conditional expectation of the loss variable given that it is greater than its 95-th percentile. The natural non-parametric estimator of the CTE is its empirical version, which happens to be always downward biased, with the bias being significantly large in small samples. In this talk we will present some theoretical results on the bias of the empirical CTE, and on some methods for bias correction.

Copyright c. 2009 The University of Iowa. All Rights Reserved. Photography c. UI Photo Service and University Relations, University of Iowa This page was last modified on Monday, 26-Oct-2009 14:22:43 CDT . /me