Publication: Estimación de volatilidad constante por métodos clásicos y bayesianos en un mercado financiero: Una aplicación a las preferenciales de Bancolombia
Loading...
Files
Identifiers
Publication date
Reading date
Event date
Start date of the public exhibition period
End date of the public exhibition period
Authors
Cortés-García, Christian
Cangrejo-Esquivel, Alvaro
Advisors
Authors of photography
Person who provides the photography
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Pablo de Olavide
Abstract
En este trabajo se proponen métodos, desde un enfoque clásico y bayesiano, para estimar la volatilidad constante de un activo cuando no es conveniente ajustar modelos de volatilidad heteroscedástica o estocástica en relación con la serie muestral del activo donde no se observa un aumento elevado de la volatilidad. Para probar cuál de los métodos propuestos se ajusta mejor a la variabilidad de la información y de los pronósticos, se utiliza el modelo estocástico propuesto por Paul Samuelson para estimar, con mínimo error, los precios de cierre de las acciones preferenciales de Bancolombia en un periodo muestral donde no se observa saltos significativos en la evolución de sus precios. Desde el enfoque bayesiano, se asumen a priori las distribuciones gamma inversa, estándar de Levy y de volatilidad de Jeffreys, con la estimación de los hiperparámetros propuestos por los autores. La metodología propuesta se contrasta con la estimación clásica de la volatilidad y el método bootstrap. A partir de los precios de cierre de la acción preferencial de Bancolombia durante un periodo de tiempo donde no existe significancia en el aumento o disminución en su volatilidad de manera temporal, la técnica bayesiana con distribución a priori Gamma Inversa captura la mayor información sobre la muestra de sus retornos, mientras que la estimación clásica de volatilidad pronostica el activo, dentro y fuera de muestra, con menor error. Sin embargo, los pronósticos del activo utilizando técnicas bayesianas o clásicas no muestran un impacto significativo.
In this paper we propose methods, from a classical and Bayesian approach, to estimate the constant volatility of an asset when it is not appropriate to fit heteroscedastic or stochastic volatility models relative to the sample series of the asset where no large increase in volatility is observed. To test which of the proposed methods best adapts to the variability of information and forecasts, the stochastic model proposed by Paul Samuelson is used to estimate, with minimum error, the closing prices of Bancolombia’s preference shares in a sample period in which no significant jumps in the evolution of their prices are observed. From the Bayesian approach, the inverse gamma, standard Levy and Jeffreys volatility distributions are assumed a priori, with the estimation of the hyperparameters proposed by the authors. The proposed methodology is compared with classical volatility estimation and the bootstrap method. From the closing prices of Bancolombia’s preference shares over a period where there is no significant increase or decrease in volatility over time, the Bayesian technique with gamma inverse prior captures the most information about sample returns, while the classical volatility estimation forecasts the asset, in and out of sample, with less error. However, forecasting the asset using either Bayesian or classical techniques does not show a significant impact.
In this paper we propose methods, from a classical and Bayesian approach, to estimate the constant volatility of an asset when it is not appropriate to fit heteroscedastic or stochastic volatility models relative to the sample series of the asset where no large increase in volatility is observed. To test which of the proposed methods best adapts to the variability of information and forecasts, the stochastic model proposed by Paul Samuelson is used to estimate, with minimum error, the closing prices of Bancolombia’s preference shares in a sample period in which no significant jumps in the evolution of their prices are observed. From the Bayesian approach, the inverse gamma, standard Levy and Jeffreys volatility distributions are assumed a priori, with the estimation of the hyperparameters proposed by the authors. The proposed methodology is compared with classical volatility estimation and the bootstrap method. From the closing prices of Bancolombia’s preference shares over a period where there is no significant increase or decrease in volatility over time, the Bayesian technique with gamma inverse prior captures the most information about sample returns, while the classical volatility estimation forecasts the asset, in and out of sample, with less error. However, forecasting the asset using either Bayesian or classical techniques does not show a significant impact.
Doctoral program
Related publication
Research projects
Description
Bibliographic reference
Revista de métodos cuantitativos para la economía y la empresa, ISSN-e 1886-516X, Vol. 40, 2025, págs. 1-24




