Stéphane Surprenant

We produce forecasts for four risk scenarios to consider their usefulness for monitoring the Canadian economy. We find a high-oil-price scenario benefits the economy, a US recession induces a slowdown, a tight labor market leads to price increases, and a restrictive monetary policy scenario increases the unemployment rate while lowering the inflation rate.

This paper provides an extensive evaluation of the performance of quantile vector autoregression (QVAR) to forecast macroeconomic risk. Generally, QVAR outperforms standard benchmark models. Moreover, QVAR and QVAR augmented with factors perform equally well. Both are adequate for modeling macroeconomic risks.