Una revisión de los modelos de volatilidad estocástica

In economics, a good part of the processes observed over time arise as the result of effects of latent variables, ie processes not directly observable. This is the case of the volatility of financial market returns, which has been shaped since the early 80s using ARCH and GARCH conditional variance models, and more recently stochastic volatility models (SV), which present fewer parameters than GARCH models and allow us to study the non-linear nature of volatility. Because in the SV model is not known accurately the likelihood function, the method of maximum quasi-likelihood is used. This method uses the representation in state-space model form. The SV model representation is evaluated through adaptive filters, such as Kalman, which implies a higher computational cost. 

• Autores: Tamayo Medina, Ronne; Rodríguez Pinzón, Heivar Yesid
• Fecha de publicación: 2010
• Institución: Universidad Santo Tomás
• Repositorio: Universidad Santo Tomás
• Idioma: spa
• OAI Identifier: oai:repository.usta.edu.co:11634/39542
• Acceso en línea: https://revistas.usantotomas.edu.co/index.php/estadistica/article/view/32; http://hdl.handle.net/11634/39542
• Palabra clave: Filtro Kalman; modelos de estado-espacio; modelos de volatilidad estocástica
• License: http://purl.org/coar/access_right/c_abf2