Pierre Guérin


Markov‐Switching Three‐Pass Regression Filter

We introduce a new approach for the estimation of high-dimensional factor models with regime-switching factor loadings by extending the linear three-pass regression filter to settings where parameters can vary according to Markov processes.
Content Type(s): Staff Research, Staff Working Papers Topic(s): Econometric and statistical methods JEL Code(s): C, C2, C22, C23, C5, C53

What Are the Macroeconomic Effects of High-Frequency Uncertainty Shocks

Staff Working Paper 2016-25 Laurent Ferrara, Pierre Guérin
This paper evaluates the effects of high-frequency uncertainty shocks on a set of low-frequency macroeconomic variables that are representative of the U.S. economy. Rather than estimating models at the same common low-frequency, we use recently developed econometric models, which allows us to deal with data of different sampling frequencies.

Predictive Ability of Commodity Prices for the Canadian Dollar

Staff Analytical Note 2016-2 Kimberly Berg, Pierre Guérin, Yuko Imura
Recent sharp declines in commodity prices and the simultaneous depreciation of the Canadian dollar (CAD) relative to the U.S. dollar (USD) have rekindled an interest in the relationship between commodity prices and the CAD-USD exchange rate.

The Dynamics of Capital Flow Episodes

Staff Working Paper 2016-9 Christian Friedrich, Pierre Guérin
This paper proposes a novel methodology for identifying episodes of strong capital flows based on a regime-switching model. In comparison with the existing literature, a key advantage of our methodology is to estimate capital flow regimes without the need for context- and sample-specific assumptions.

Model Averaging in Markov-Switching Models: Predicting National Recessions with Regional Data

Staff Working Paper 2015-24 Pierre Guérin, Danilo Leiva-Leon
This paper introduces new weighting schemes for model averaging when one is interested in combining discrete forecasts from competing Markov-switching models. In particular, we extend two existing classes of combination schemes – Bayesian (static) model averaging and dynamic model averaging – so as to explicitly reflect the objective of forecasting a discrete outcome.

See More


Follow the Bank