Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Ensayos sobre POLÍTICA ECONÓMICA
Print version ISSN 0120-4483
Abstract
LONDONO, Charle Augusto. Quantile Regression Model Applied to Artificial Neural Networks. An Approximation of the Structure Caviar for the Colombian Stock Market. Ens. polit. econ. [online]. 2011, vol.29, n.spe64, pp.62-109. ISSN 0120-4483.
There are different methodologies for calculating Value at Risk (VaR) seeking to capture market risk primarily exposed to financial institutions. As the conditional autoregressive Value at Risk (CAViaR) model of Engle y Manganelli (1999, 2001, 2004) a good empirical approximation to the true measure VaR, both to cover the risk, as for compliance with banking regulations. Therefore, the objective of this paper is to approach the model CAViaR for the Colombian stock market using different macroeconomic risk factors and financial as outlined in Chernozhukov and Umantsev (2001), it also seeks to establish empirical rule allows better capture the behavior of the General Index of the Stock Exchange of Colombia (GISEC).
Keywords : conditional autoregressive Value at Risk; regression quantile; artificial neural networks; macroeconomics and financial variable; banking regulation; financial market.