A seminar by Professor Marcos Escobar from Western University Canada
Title: Portfolio Optimization in Affine GARCH models.
Abstract: Affine GARCH models, pioneered by Heston and Nandi (2000), combine the observation-driven estimation advantages of discrete-time GARCH with the exponential-affine tractability familiar from continuous-time stochastic-volatility models. This talk surveys a roughly half-decade research program on dynamic portfolio choice within this class. The key step is a second-order approximation to log self-financing that preserves affine wealth dynamics; under this approximation, the discrete-time Bellman recursion closes in exponential-affine form and yields analytical portfolio rules for a broad class of Affine GARCH specifications. I develop the core method through two benchmark results: a single-asset CRRA allocation and its multi-asset extension under a parsimonious CAPM-style specification. I then examine the accuracy and economic cost of the approximation and survey extensions to non-Gaussian innovations, alternative preferences, derivatives, and Bayesian parameter uncertainty, together with ongoing directions involving bonds, commodities, VIX, and other affine markets.
For further information, please contact RSFAS Seminars.
All information collected by the University is governed by the ANU Privacy Policy.

