Photo by whaleitsjessica from unsplash
Abstract In the present paper we discuss the forecasting ability of the VaR model, within the context of a Generalized Autoregressive Score (GAS). The proposed method considers an Asymmetric Laplace… Click to show full abstract
Abstract In the present paper we discuss the forecasting ability of the VaR model, within the context of a Generalized Autoregressive Score (GAS). The proposed method considers an Asymmetric Laplace Distribution (GAS-ALD) to describe the daily log-returns of the analyzed data. A forecastability indicator for a certain probability of VaR is proposed. The approach uses back-testing and several unconditional and conditional tests, to see whether or not the GAS-ALD model accurately describes the specificity of log-returns’ distribution. Our results show a strong connection between this indicator and the informational efficiency of financial markets, as it indirectly reflects shifts in market efficiency.
Journal Title: Finance Research Letters
Year Published: 2021
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!