Advanced

A Simulation Study comparing MCMC, QML and GMM Estimation of the Stochastic Volatility Model

Nilsson, Carl LU (2016) NEKN01 20141
Department of Economics
Abstract
The stochastic volatility (SV) model is an alternative to GARCH models to model time varying volatility. In this thesis the basic stochastic volatility model and three different estimation methods are described---namely, Bayesian Markov chain Monte Carlo (MCMC) methods, quasi maximum-likelihood (QML) and generalized method of moments (GMM).

To compare these estimation methods a large scale simulation study is conducted where many different parameter values and sample sizes are compared. Since both the latter two methods are non-likelihood based, our hypothesis is that the likelihood based MCMC would perform better. The conclusion of the study is that this is the case, MCMC turns out to be more efficient than QML and GMM by quite a... (More)
The stochastic volatility (SV) model is an alternative to GARCH models to model time varying volatility. In this thesis the basic stochastic volatility model and three different estimation methods are described---namely, Bayesian Markov chain Monte Carlo (MCMC) methods, quasi maximum-likelihood (QML) and generalized method of moments (GMM).

To compare these estimation methods a large scale simulation study is conducted where many different parameter values and sample sizes are compared. Since both the latter two methods are non-likelihood based, our hypothesis is that the likelihood based MCMC would perform better. The conclusion of the study is that this is the case, MCMC turns out to be more efficient than QML and GMM by quite a large margin, especially for estimating the latent volatilities. (Less)
Please use this url to cite or link to this publication:
author
Nilsson, Carl LU
supervisor
organization
course
NEKN01 20141
year
type
H1 - Master's Degree (One Year)
subject
keywords
Monte Carlo simulation, stochastic volatility, Markov chain Monte Carlo, quasi-maximum likelihood, generalized method of moments
language
English
id
8893766
date added to LUP
2016-10-20 11:04:39
date last changed
2016-10-20 11:04:39
@misc{8893766,
  abstract     = {The stochastic volatility (SV) model is an alternative to GARCH models to model time varying volatility. In this thesis the basic stochastic volatility model and three different estimation methods are described---namely, Bayesian Markov chain Monte Carlo (MCMC) methods, quasi maximum-likelihood (QML) and generalized method of moments (GMM). 

To compare these estimation methods a large scale simulation study is conducted where many different parameter values and sample sizes are compared. Since both the latter two methods are non-likelihood based, our hypothesis is that the likelihood based MCMC would perform better. The conclusion of the study is that this is the case, MCMC turns out to be more efficient than QML and GMM by quite a large margin, especially for estimating the latent volatilities.},
  author       = {Nilsson, Carl},
  keyword      = {Monte Carlo simulation,stochastic volatility,Markov chain Monte Carlo,quasi-maximum likelihood,generalized method of moments},
  language     = {eng},
  note         = {Student Paper},
  title        = {A Simulation Study comparing MCMC, QML and GMM Estimation of the Stochastic Volatility Model},
  year         = {2016},
}