Author
Listed:
- Gómez Romero, Juan Manuel
- Jiménez Moscoso, José Alfredo
Abstract
Resumen: En búsqueda de generar estrategias de inversión en pro de maximizar el rendimiento esperado y minimizar el riesgo, se estudian dos modelos de selección de portafolios óptimos. El primero se ajusta usando rendimientos logarítmicos, y en el segundo se emplea análisis de componentes principales (ACP) a estos rendimientos. Luego, para cada uno de ellos se establece su rendimiento ponderado y se crean unas medidas para establecer los estados de las cadenas de Markov de primer y segundo orden. Esto permite pronosticar si los portafolios conformados tendrán comportamientos alcistas o bajistas dadas las probabilidades de los estados de las cadenas de Markov. Se realiza una aplicación usando los retornos de precios de cierre diarios de 21 acciones del COLCAP, para el periodo comprendido desde enero de 2014 a octubre de 2017. Se concluye que en el mercado colombiano un portafolio conformado bajo ACP de los rendimientos tiene una mayor rentabilidad esperada y un menor riesgo a largo plazo, teniendo una precisión de pronóstico del modelo dados los vectores estacionarios de las cadenas de Markov. Abstract: Searching for create investment strategies in pursuit of maximizing the expected return on investment and minimizing the risk two models of selection of optimal portfolios are studied. The first portfolio composition model is adjusted using logarithmic returns, and the other uses principal component analysis (PCA) at these returns. Then, for each of them its weighted performance is established and measures are created to establish the states of the first and second order Markov chains, this allows to predict whether the shaped portfolios will have bullish or bearish behaviors given the probabilities of the states of the Markov chains. An application is made using the daily closing price returns of 21 COLCAP shares for the period from January 2014 to October 2017. Concluding that in the Colombian Market a portfolio formed by PCA of the returns has a higher expected profitability and less risk in the long term, having an accuracy of model’s forecast according with the stationary vectors of the Markov chains. Résumé: Lorsqu’il s’agit de rechercher des stratégies d’investissement qui maximisent le rendement attendu et qui minimisent le risque, deux modeles de sélection de portefeuille optimal sont souvent étudiés. Le premier modele est ajusté a l’aide des rendements logarithmiques, tandis que le second applique l’analyse en composantes principales (ACP) a ces rendements. Ensuite, pour chaque modele, on établit son rendement pondéré et des mesures sont créées pour établir les états des chaines de Markov du premier et du deuxieme ordre. Cela permet de savoir si les portefeuilles formés auront des comportements haussiers ou baissiers, compte tenu des probabilités des états des chaines de Markov. Une application est faite en utilisant les rendements quotidiens de cloture de 21 actions COLCAP, pour la période de janvier 2014 a octobre 2017. On conclu que sur le marché colombien un portefeuille formé en ACP a une rentabilité attendue plus élevé et un risque inférieur a long terme. La précision de cette prévision est donnée par les vecteurs stationnaires des chaines de Markov.
Suggested Citation
Gómez Romero, Juan Manuel & Jiménez Moscoso, José Alfredo, 2020.
"Selección óptima de portafolios basada en cadenas de Markov de primer y segundo orden,"
Revista Lecturas de Economía, Universidad de Antioquia, CIE, issue No. 92, pages 33-66, January.
Handle:
RePEc:col:000174:019569
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:col:000174:019569. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Universidad de Antioquia. Facultad de Ciencias Economicas. (Laura Maria Posada Arboleda) (email available below). General contact details of provider: https://edirc.repec.org/data/ciantco.html .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.