Biblioteca Digital de VanguardiaPricing Derivatives Securities with Prior Information on Long- Memory Volatility
This paper investigates the existence of long memory in the volatility of the Mexican stock market. We use a stochastic volatility (SV) model to derive statistical test for changes in volatility. In this case, estimation is carried out through the Kalman filter (KF) and the improved quasi-maximum li...
| Autores principales: | , |
|---|---|
| Formato: | artículo científico |
| Lenguaje: | Inglés |
| Publicado: |
Centro de Investigación y Docencia Económicas, A.C.
2003
|
| Materias: | |
| Acceso en línea: | http://www.redalyc.org/articulo.oa?id=32312104 http://biblioteca-repositorio.clacso.edu.ar/handle/CLACSO/82834 |
| Sumario: | This paper investigates the existence of long memory in the volatility of the Mexican stock market. We use a stochastic volatility (SV) model to derive statistical test for changes in volatility. In this case, estimation is carried out through the Kalman filter (KF) and the improved quasi-maximum likelihood (IQML). We also test for both persistence and long memory by using a long-memory stochastic volatility (LMSV) model, constructed by including an autoregressive fractionally integrated moving average (ARFIMA) process in a stochastic volatility scheme. Under this framework, we work up maximum likelihood spectral estimators and bootstraped confidence intervals. In the light of the empirical findings, we develop a Bayesian model for pricing derivative securities with prior information on long-memory volatility. |
|---|