首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Likelihood-Based comparison of stable paretian and competing models: Evidence from daily exchange rates
Abstract:

Considering alternative models for exchange rates has always been a central issue in applied research. Despite this fact, formal likelihood-based comparisons of competing models are extremely rare. In this paper, we apply the Bayesian marginal likelihood concept to compare GARCH, stable, stable GARCH, stochastic volatility, and a new stable Paretian stochastic volatility model for seven major currencies. Inference is based on combining Monte Carlo methods with Laplace integration. The empirical results show that neither GARCH nor stable models are clear winners, and a GARCH model with stable innovations is the model best supported by the data.
Keywords:Stable Distribution  Bayesian Analysis  Unit Roots  Garch  Stochastic Volatility  Exchange Rates
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号