Measuring Systemic Risk: A Quantile Factor Analysis

This paper proposes a novel measure to quantify systemic risk from the information contained in asset returns. In the context of the external habits formation model of Campbell and Cochrane (1999), and under the assumption that stock returns are heteroskedastic, I show that equilibrium risk premium has a factor structure where the factors are a monotonic transformation of the surplus consumption ratio, a state variable that captures the systemic risk in the structural model. The restrictions implied by the model suppose a setup where one of the factors affects the variance of excess returns. Therefore, the factor model is estimated employing an adapted version of the Quantile Principal Components estimation procedure proposed by Sagner (2019). Simulations of the structural model under alternative parameterizations calibrated for the US show a good performance of the proposed systemic risk metric computed at quantiles different than the median. When estimated using quarterly post-war data, the proposed measure displays significant hikes that coincide with both several US recession periods and episodes of substantial financial market turbulences. Finally, the systemic risk estimator can forecast sharp shifts in both economic activity and industrial production up to one quarter ahead.