Bayesian Forecast Combination for Inflation Using Rolling Windows: An Emerging Country Case
The series Working Papers on Economics is published by the Office for Economic Studies at the Banco de la República (Central Bank of Colombia). The works published are provisional, and their authors are fully responsible for the opinions expressed in them, as well as for possible mistakes. The opinions expressed herein are those of the authors and do not necessarily reflect the views of Banco de la República or its Board of Directors.
Typically, when forecasting inflation rates, there are a variety of individual models and a combination of several of these models. We implement a Bayesian shrinkage combination methodology to include information that is not captured by the individual models using expert forecasts as prior information. To take into account two common characteristics in emerging countries’ economies, possible parameter instabilities and non-stationary dynamics, we use a rolling estimation windows technique for series integrated of order one. The empirical results of Colombian inflation show that the Bayesian forecast combination model outperforms the individual models and the random walk predictions for every evaluated forecast horizon. Moreover, these results outperform shrinkage forecasts that consider other priors as equal or zero weights.
