Estimation of Dynamic Bivariate Mixture Models
- 1 October 2003
- journal article
- Published by Informa UK Limited in Journal of Business & Economic Statistics
- Vol. 21 (4), 570-576
- https://doi.org/10.1198/073500103288619287
Abstract
This note compares a Bayesian Markov chain Monte Carlo approach implemented by Watanabe with a maximum likelihood ML approach based on an efficient importance sampling procedure to estimate dynamic bivariate mixture models. In these models, stock price volatility and trading volume are jointly directed by the unobservable number of price-relevant information arrivals, which is specified as a serially correlated random variable. It is shown that the efficient importance sampling technique is extremely accurate and that it produces results that differ significantly from those reported by Watanabe.Keywords
This publication has 13 references indexed in Scilit:
- ECONOMETRIC MODELLING OF UK HOUSE PRICES USING ACCELERATED IMPORTANCE SAMPLING*Oxford Bulletin of Economics and Statistics, 2009
- Stochastic volatility models: conditional normality versus heavy-tailed distributionsJournal of Applied Econometrics, 2000
- Dynamic Bivariate Mixture Models: Modeling the Behavior of Prices and Trading VolumeJournal of Business & Economic Statistics, 1998
- Likelihood analysis of non-Gaussian measurement time seriesBiometrika, 1997
- Return Volatility and Trading Volume: An Information Flow Interpretation of Stochastic VolatilityThe Journal of Finance, 1996
- Understanding the Metropolis-Hastings AlgorithmThe American Statistician, 1995
- Bayesian Analysis of Stochastic Volatility ModelsJournal of Business & Economic Statistics, 1994
- Accelerated gaussian importance sampler with application to dynamic latent variable modelsJournal of Applied Econometrics, 1993
- Simulation and the Asymptotics of Optimization EstimatorsEconometrica, 1989
- A Method of Simulated Moments for Estimation of Discrete Response Models Without Numerical IntegrationEconometrica, 1989