Compounding Political and Energy Risks: A clustered stochastic COVOL model
This paper aims to investigate the relationship between different sources of risk related to energy, that is, returns on the energy sector, energy uncertainty, and geopolitical risk. To this aim, we provide a parsimonious and flexible model for extracting common volatility factors (COVOL) from a cross-section of assets. We assume there are groups of assets with different exposure levels across the groups and similar levels within each group. The membership of the assets to the groups is unknown, which naturally calls for using stochastic partition models. The latent factors have a gamma autoregressive structure, which allows for persistence. We provide some theoretical properties of the new clustered COVOL model, a Bayesian inference procedure well suited for latent variable models, and an empirical analysis of the volatility transmission in a multi-country perspective.
Area:
Keywords: Volatility comovements, Geopolitical risk, Uncertainty, Energy markets, Transmission channels
Please Login in order to download this file