|
Activity Number:
|
462
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
| Abstract - #303690 |
|
Title:
|
EMM MCMC and Bayesian Parameter Estimation for a Partially Observed Nonlinear Diffusion Process
|
|
Author(s):
|
Paul Schneider*+ and Osnat Stramer
|
|
Companies:
|
University of Warwick and The University of Iowa
|
|
Address:
|
, , International, ,
|
|
Keywords:
|
EMM MCMC ; Bayesian Estimation ; Stochastic Volatility
|
|
Abstract:
|
This paper investigates estimators produced by the Efficient Method of Moments (EMM) and Bayesian Markov chain Monte Carlo techniques. The study is performed conditional on a nonlinear diffusion model comprising partially observed state variables that fits S&P 100 index data well. We introduce novel state-updating schemes for Bayesian estimation and tractable auxiliary models for EMM estimation under stochastic volatility.
|
