Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia

This research explores various methods to estimate Value at Risk for a portfolio of high and medium liquidity Colombian stocks. It concludes that, according to the characteristics of these assets, Full Montecarlo is more robust than other parametric methods –particularly the Normal method-, and the...

ver descrição completa

Detalhes bibliográficos
Autores: María Auxiliadora Vergara Cogollo, Cecilia Maya Ochoa
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2019
País:Colombia
Recursos:Universidad EAFIT
Repositorio:Repositorio EAFIT
Idioma:español
OAI Identifier:oai:repository.eafit.edu.co:10784/14018
Acesso em linha:http://hdl.handle.net/10784/14018
Access Level:acceso abierto
Palavra-chave:VaR
Market Risk
Full Montecarlo
Garch
Egarch
Parch
Aparch.
riesgo de mercado
método Montecarlo Estructurado
id CO_f7f5b89b02431fbd71ca7bacc06dbb59
oai_identifier_str oai:repository.eafit.edu.co:10784/14018
network_acronym_str CO
network_name_str Colombia
repository_id_str
spelling Structured Monte Carlo. Estimated value at risk in a stock portfolio in ColombiaMontecarlo estructurado. Estimación del valor en riesgo en un portafolio accionario en ColombiaMaría Auxiliadora Vergara CogolloCecilia Maya OchoaVaRMarket RiskFull MontecarloGarchEgarchParchAparch.VaRriesgo de mercadométodo Montecarlo EstructuradoGarchThis research explores various methods to estimate Value at Risk for a portfolio of high and medium liquidity Colombian stocks. It concludes that, according to the characteristics of these assets, Full Montecarlo is more robust than other parametric methods –particularly the Normal method-, and the historical simulation. However, to avoid model risk, it requires a correct specification of the stochastic process followed by each of the risk factors. Given the evidence of fat tails on the return series, volatility models such as GARCH, EGARCH, PARCH and APARCH are used for this purpose. After that, we compare the one-step ahead VaR forecast given by these models with the one obtained by parametric methods. It is found that Garch models predict VaR better since they capture the fat tails characteristic of these series. Once the stochastic process for each asset is properly identified, the Full Montecarlo is applied to estimate VaR.De acuerdo con el estudio que se presenta, por las características de los activos que lo conforman, el método de Montecarlo Estructurado es el más completo y robusto para la medición del valor en riesgo (VaR) de un portafolio hipotético de acciones colombianas de alta y mediana bursatilidad, en comparación con métodos paramétricos o de simulación histórica. Sin embargo, para su aplicación, es necesaria una cuidadosa modelación del comportamiento de las distintas variables de riesgo. La presencia de colas pesadas en las series de retornos de estos activos obliga al uso de modelos de volatilidad del tipo GARCH, EGARCH, PARCH y APARCH. Se evalúa su capacidad de pronóstico del VaR del periodo siguiente en paralelo con el obtenido por el método Normal. Los modelos tipo Garch pronostican mejor el VaR, puesto que logran capturar el efecto de colas pesadas en las series. Definido el proceso estocástico que siguen los activos, se procede a su cálculo con Montecarlo Estructurado.Universidad EAFITUniversidad EAFIT13/12/20092019-10-04T14:30:46Z13/12/20092019-10-04T14:30:46Zarticleinfo:eu-repo/semantics/articlepublishedVersioninfo:eu-repo/semantics/publishedVersionArtículotext/htmlapplication/pdftext/html2256-43221692-0279http://hdl.handle.net/10784/14018AD-minister: No 15 (2009)reponame:Repositorio EAFITinstname:Universidad EAFITinstacron:Universidad EAFITspahttp://publicaciones.eafit.edu.co/index.php/administer/article/view/204http://publicaciones.eafit.edu.co/index.php/administer/article/view/204Medellín de: Lat: 06 15 00 N degrees minutes Lat: 6.2500 decimal degrees Long: 075 36 00 W degrees minutes Long: -75.6000 decimal degreesCopyright © 2009 María Auxiliadora Vergara Cogollo, Cecilia Maya Ochoainfo:eu-repo/semantics/openAccessAcceso abierto2019-11-30T14:22:07Z
dc.title.none.fl_str_mv Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia
Montecarlo estructurado. Estimación del valor en riesgo en un portafolio accionario en Colombia
title Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia
spellingShingle Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia
María Auxiliadora Vergara Cogollo
VaR
Market Risk
Full Montecarlo
Garch
Egarch
Parch
Aparch.
VaR
riesgo de mercado
método Montecarlo Estructurado
Garch
title_short Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia
title_full Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia
title_fullStr Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia
title_full_unstemmed Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia
title_sort Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia
dc.creator.none.fl_str_mv María Auxiliadora Vergara Cogollo
Cecilia Maya Ochoa
author María Auxiliadora Vergara Cogollo
author_facet María Auxiliadora Vergara Cogollo
Cecilia Maya Ochoa
author_role author
author2 Cecilia Maya Ochoa
author2_role author
dc.contributor.none.fl_str_mv Universidad EAFIT
dc.subject.none.fl_str_mv VaR
Market Risk
Full Montecarlo
Garch
Egarch
Parch
Aparch.
VaR
riesgo de mercado
método Montecarlo Estructurado
Garch
topic VaR
Market Risk
Full Montecarlo
Garch
Egarch
Parch
Aparch.
VaR
riesgo de mercado
método Montecarlo Estructurado
Garch
description This research explores various methods to estimate Value at Risk for a portfolio of high and medium liquidity Colombian stocks. It concludes that, according to the characteristics of these assets, Full Montecarlo is more robust than other parametric methods –particularly the Normal method-, and the historical simulation. However, to avoid model risk, it requires a correct specification of the stochastic process followed by each of the risk factors. Given the evidence of fat tails on the return series, volatility models such as GARCH, EGARCH, PARCH and APARCH are used for this purpose. After that, we compare the one-step ahead VaR forecast given by these models with the one obtained by parametric methods. It is found that Garch models predict VaR better since they capture the fat tails characteristic of these series. Once the stochastic process for each asset is properly identified, the Full Montecarlo is applied to estimate VaR.
publishDate 2019
dc.date.none.fl_str_mv 13/12/2009
13/12/2009
2019-10-04T14:30:46Z
2019-10-04T14:30:46Z
dc.type.none.fl_str_mv article
info:eu-repo/semantics/article
publishedVersion
info:eu-repo/semantics/publishedVersion
Artículo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv 2256-4322
1692-0279
http://hdl.handle.net/10784/14018
identifier_str_mv 2256-4322
1692-0279
url http://hdl.handle.net/10784/14018
dc.language.none.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv http://publicaciones.eafit.edu.co/index.php/administer/article/view/204
http://publicaciones.eafit.edu.co/index.php/administer/article/view/204
dc.rights.none.fl_str_mv Copyright © 2009 María Auxiliadora Vergara Cogollo, Cecilia Maya Ochoa
info:eu-repo/semantics/openAccess
Acceso abierto
rights_invalid_str_mv Copyright © 2009 María Auxiliadora Vergara Cogollo, Cecilia Maya Ochoa
Acceso abierto
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
application/pdf
text/html
dc.coverage.none.fl_str_mv Medellín de: Lat: 06 15 00 N degrees minutes Lat: 6.2500 decimal degrees Long: 075 36 00 W degrees minutes Long: -75.6000 decimal degrees
dc.publisher.none.fl_str_mv Universidad EAFIT
publisher.none.fl_str_mv Universidad EAFIT
dc.source.none.fl_str_mv AD-minister: No 15 (2009)
reponame:Repositorio EAFIT
instname:Universidad EAFIT
instacron:Universidad EAFIT
instname_str Universidad EAFIT
instacron_str Universidad EAFIT
institution Universidad EAFIT
reponame_str Repositorio EAFIT
collection Repositorio EAFIT
_version_ 1825051027799277568
score 15,198674

Registos relacionados