Multivariate Dependence Risk and Portfolio Optimization: An Application to Mining Stock Portfolios

Dependence between the global gold market and emerging stock markets (E7+1): Evidence from Granger causality using quantile and quantile‐on‐quantile regression methods

“…The literature on the dynamic relations among various commodity prices and the stock market is extensive and widespread across major regions of the world. These relations have been explored for the global market (Kang, McIver, & Yoon, ; Reboredo & Ugolini, ; Sadorsky, ), cross countries (Ciner, Gurdgiev, & Lucey, ; Choudhry, Hassan, & Shabi, ; Raza, Shahzad, Tiwari, and Shahbaz (), Asia (Arouri, Lahiani, & Nguyen, ; Bouri, Jain, Biswal, & Roubaud, 2017a; Bouri, Roubaud, Jammazi, & Assaf, 2017b; Huang, An, Gao, & Huang, ; Kumar, ; Mensi, Hammoudeh, Reboredo, & Nguyen, ; Ziaei, ), Europe (Charlot & Marimoutou, ; Hoang, Lean, & Wong, ; Shahzad, Raza, Shahbaz, & Ali, ), United States (Akgül, Bildirici, & Özdemir, ; Baruník, Kočenda, & Vácha, ; Baumöhl & Lyócsa, ; Bekiros, Nguyen, Uddin, & Sjö, ; Creti, Joëts, & Mignon, ; Gokmenoglu & Fazlollahi, ; Hood & Malik, ; Mensi, Beljid, Boubaker, & Managi, ) and Australia (Bekiros, Hernandez, Hammoudeh, & Nguyen, ).…”

Pair-Copula Constructions for Financial Applications: A Review

“…This model is found to produce the highest-ranked outcomes across a range of statistical and economic metrics when compared to other models incorporating elliptical or symmetric dependence structures. Other papers that shows the usefulness of pair-copula constructions for portfolio optimization are [101][102][103].…”

Global financial crisis and dependence risk analysis of sector portfolios: a vine copula approach

“…These bivariate copula-based models have become increasingly popular in the empirical domain for the analysis of multivariate real-world datasets since they allow for the estimation of random vector distributions through the assessment of copulas and marginals separately. The flexibility of these models enables one to overcome the limitations of traditional measures of dependence (e.g., bivariate copulas) and correlation (e.g., Pearson correlation), and leads to more accurate estimation of the dependence structure (Bekiros et al, 2015;Arreola-Hernandez, 2014;Aloui et al, 2011). 4 The graphical characteristic of the pair vine copulas also enables a localized and specific-specialized modeling of marginal and joint distributional features such as kurtosis, skewness, symmetric and asymmetric dependence, through the use of bivariate copulas serving as the building blocks (Czado, 2010;Brechmann and Schepsmeier, 2011;Czado et al, 2012).…”