Title: A Change-of-Variables Approach to Simulating Conditional Expectations
Speaker: Guangwu Liu, City University of Hong Kong
Time: 14:00-15:00, pm., 19, Jun. (Fri.), 2015.
Venue: Room 404, Tongji Building A
Abstract:
Typically crude Monte Carlo estimators do not perform well when estimating conditional expectations, which may be expectations conditioned on a probability-zero event. In this talk we introduce a change-of-variables approach to simulating conditional expectations. At the heart of the proposed approach is the construction of a one-to-one mapping such that a conditional expectation can be represented as an ordinary expectation by using change-of-variables technique. This new representation leads to an efficient estimator of the conditional expectation. Application to Greek estimation for financial options will be discussed.
A Short Bio:
Dr. Guangwu Liu is currently an assistant professor in the Department of Management Sciences at City University of Hong Kong. His research interests include stochastic simulation, financial engineering and risk management. His work has been published in flagship journals in the field, including Operations Research, and Management Science.