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.
I develop a method for Bayesian estimation of globally solved, non-linear macroeconomic models. The method uses a mixture density network to approximate the initial state distribution. The mixture density network results in more reliable posterior inference compared with the case when the initial states are set to their steady-state values.
We assess whether unconventional monetary and fiscal policy implemented in response to the COVID-19 pandemic in the U.S. contribute to the 2021-2023 inflation surge through the lens of several different empirical methodologies and establish a null result.
We explain how the Bank of Canada’s policy models capture the trade-off between output and inflation in Canada. We provide new estimates of the trade-off and contrast them with those in the Bank’s macroeconomic models.
We quantitively assess the risks of a wage-price spiral occurring in Canada over history. We find the risk of a wage-price spiral increases when the inflation expectations become unanchored and the credibility of central banks declines.
We assess the health of the Canadian labour market. We find that it has seen gradual but material easing since 2023, amid some signs of structural changes.
We forecast recessions in Canada using an autoregressive (AR) probit model. The results highlight the short-term predictive power of the US economic activity and suggest that financial indicators are reliable predictors of Canadian recessions. In addition, the suggested model meaningfully improves the ability to forecast Canadian recessions, relative to a variety of probit models proposed in the Canadian literature.