Las decisiones financieras se pueden dividir en decisiones de inversión y decisiones de financiación. En lo que respecta a las decisiones de inversión, la incertidumbre acerca de la dinámica futura de las variables económicas y de las financieras tiene un rol fundamental. Eso, se explica porque los retornos esperados por las empresas y por los inversionistas se pueden ver afectados por los movimientos adversos en los mercados financieros y por los altos niveles de volatilidad. Como consecuencia, resulta crucial realizar un adecuado análisis y modelación de la volatilidad para el proceso de toma de decisiones financieras, por parte de las empresas y el diseño de estrategias de inversión y cobertura por parte de los inversionistas. En este sentido, el estudio de la volatilidad se ha convertido en uno de los temas más interesantes de la investigación en finanzas. Lo anterior ha cobrado mayor relevancia en los últimos años, teniendo en cuenta el escenario de alta volatilidad e incertidumbre que afrontan los mercados a nivel global. Este documento tiene como objetivo abordar cuatro cuestiones centrales, las cuales están relacionadas con la volatilidad financiera como campo de investigación. Esas cuestiones son, la transmisión y spillovers de volatilidad en mercados emergentes, la calibración de la superficie de volatilidad para proyectos de energía renovable y el pronóstico de los rendimientos de activos energéticos y spillovers de volatilidad a través de técnicas de machine learning.
Financial decisions can be divided in investment and financing decisions. Concerning investment decisions, the uncertainty about the future dynamics of financial and economic variables has a central role, considering that the returns expected by firms and investors can be affected by the adverse movements in financial markets and their high volatility. In consequence, the adequate volatility analysis and modeling is crucial for the firm’s financial decision-making process and the design of investing and hedging strategies by investors. In this regard, the study of volatility has become one of the most interesting topics in finance research. The foregoing has become more relevant in recent years considering the scenario of high volatility and uncertainty faced by markets globally. This document aims to address four central issues related to financial volatility as a research area. These are, volatility transmission and spillovers in Emerging Markets, the calibration of the volatility surface for renewable energy projects and the forecast of energy assets returns and volatility spillovers through machine learning techniques. In the first chapter of the document, the volatility transmission effects between an energy index and a financial index for Emerging Markets are examined. Then, by using a DCC model, it is shown that the volatility transmission effects between the employed indices for the subprime crisis and the COVID-19 pandemic were different. This, considering that the former crisis originated in the financial sector and spread to the rest of the economy, while the second originated in the real sector and trasmitted to the rest of the economy posteriorly. Considering that the relationship between markets volatility is time-varying, in the second chapter, a dynamic analysis of volatility spillovers between commodities, Bitcoin and an Emerging Markets index is developed. Employing the methodology proposed by Diebold and Yilmaz (2012), it is concluded that the volatility spillovers effects between the analyzed assets is not constant in direction and intensity over time. In particular, for periods of crisis such as the COVID-19 pandemics, there are reversals in the direction of volatility spillovers due to the sector in which the crises originate. In addition, in this chapter the dynamic nature of volatility spillovers is exploited. Hence, the volatility spillover index proposed by Diebold and Yilmaz is forecasted to be used as a measure to anticipate high turbulence periods. This, through both traditional econometric models and machine learning techniques. In the third chapter, a model for the prediction of carbon and oil prices is proposed. In this sense, a hybrid model that ensembles the forecasts obtained from different machine learning techniques and traditional econometric models is developed, obtaining results that show the advantages of employing hybrid models which combine machine learning techniques, exclusively, to forecast financial variables. In Chapter four, a methodology for the estimation of volatility in renewable energy projects valuation through real options is presented. In this methodology, which is an extension of the implied volatility approach employed for financial options, the volatility of the project is the implied volatility obtained from the volatility surface of comparable firms for a certain valuation date and given debt-to-equity relation of a renewable energy project. In this analysis, the stochastic ‘alpha-beta-rho’ model is utilized to calibrate the volatility surface for real option valuation purposes. Finally, the conclusions derived from the mentioned chapters are presented at the end of the document as well as some recommendations for future research.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados