On downside risk predictability through liquidity and trading activity: A dynamic quantile approach

Most downside risk models implicitly assume that returns are a sufficient statistic with which to forecast the daily conditional distribution of a portfolio. In this paper, we analyze whether the variables that proxy for market‐wide liquidity and trading conditions convey valid information for forecasting the quantiles of the conditional distribution of several representative market portfolios, including volume‐ and value‐weighted market portfolios, and several Book‐to‐Market‐ and Size‐sorted portfolios. Using dynamic quantile regression techniques, we report evidence of conditional tail predictability in terms of these variables. A comprehensive backtesting analysis shows that this link can be exploited in dynamic quantile modelling, in order to considerably improve the performances of day‐ahead Value at Risk forecasts.