The transition from traditional energy to cleaner energy sources has raised concerns from companies and investors regarding, among other things, the impact on financial downside risk. This article implements backtesting techniques to estimate and validate the value-at-risk (VaR) and expected shortfall (ES) in order to compare their performance among four renewable energy stocks and four traditional energy stocks from the WilderHill New Energy Global Innovation and the Bloomberg World Energy for the period 2005-2016. The models used to estimate VaR and ES are AR(1)-GARCH(1,1), AR(1)-EGARCH(1,1), and AR(1)-APARCH(1,1), all of them under either normal, skew-normal, Student’s t, skewed-t, Generalized Error or Skew-Generalized Error distributed innovations. Backtesting performance is tested through traditional Kupiec and Christoffersen tests for VaR, but also through recent backtesting ES techniques. The paper extends these tests to the skewed-t, skew-normal and Skew-Generalized Error distributions and applies it for the first time in traditional and renewable energy markets showing that the skewed-t and the Generalized Error distribution are an accurate tool for risk management in those markets. Our findings have important implications for portfolio managers and regulators in terms of capital allocation in renewable and traditional energy stocks, mainly to reduce the impact of possible extreme loss events.

No abstract

No abstract

Mergers and acquisitions (M&As) are mainly a mechanism used in the Latin American banking industry to carry out business consolidation. This paper focuses on the effect of M&A announcements on stocks of Latin American banks and their rivals between 2000 and 2019. We evaluate two impacts of M&A announcements: impacts on cumulative abnormal returns (CAR) and impacts on event-induced variance (EIV). We use the GARCH-based event-study method. We find that acquirers and target banks have a statistically significant CAR, however, the sign is inconclusive. Rivals of acquirers and targets are not affected by M&A announcements. In general, we observe that EIV is negative for acquirers, targets, and rivals. Finally, we estimate a multivariate GARCH model to isolate the effects of co-movements of volatility between the acquirer and the target, and we find that the results remain qualitatively equal.