A short term credibility index for central banks under inflation targeting: an application to Brazil

Abstract

This paper uses predictive densities obtained via mixed causalnoncausal autoregressive models to evaluate the statistical sustainability of Brazilian inflation targeting system with the tolerance bounds. The probabilities give an indication of the short-term credibility of the targeting system without requiring modelling people's beliefs. We also investigate the added value of including experts predictions of key macroeconomic variables.

Modelling and forecasting economic time series with mixed causal-noncausal models

“…Hencic and Gouriéroux (2015) use a cubic deterministic trend to isolate the bubble in the Bitcoin. Hecq and Voisin (2022) find that underestimating the order of a polynomial trend can have substantial impacts on the dynamics of the series and show that the Hodrick-Prescott (hereafter HP) filtering can be used as an alternative that does not require any assumption regarding the order of the trend. They find that with the penalising parameter suggested by Ravn and Uhlig (2002), i.e.…”

“…The MAR models employed here are univariate, hence no exogenous information is incorporated, as opposed to MARX models (see Hecq, Issler, and Telg (2020) and Hecq, Issler, and Voisin (2022)). Disregarding exogenous variables facilitates forecasting but can sometimes lead to consequential lack of information.…”

“…MAR models were introduced by Lanne, Luoto, and Saikkonen (2012) and refined by . Here we use the framework proposed in Hecq and Voisin (2021) and Hecq and Voisin (2022).…”

“…This is our benchmark case, but we also experiment with alternative specifications. Using the approach in Hecq and Voisin (2021) and Hecq and Voisin (2022), and our benchmark specification, we evaluate the probabilities that the inflation rate stays on track in the future within the announced target bounds.…”

“…Predicting crashes in oil prices during the COVID-19 pandemic with mixed causal-noncausal models Adapted from: Alain Hecq and Elisa Voisin (2022). "Predicting bubble bursts in oil prices during the COVID-19 pandemic with mixed causal-noncausal models".…”