Search Results
Report
Forecasting in large macroeconomic panels using Bayesian Model Averaging
This paper considers the problem of forecasting in large macroeconomic panels using Bayesian model averaging. Practical methods for implementing Bayesian model averaging with factor models are described. These methods involve algorithms that simulate from the space defined by all possible models. We explain how these simulation algorithms can also be used to select the model with the highest marginal likelihood (or highest value of an information criterion) in an efficient manner. We apply these methods to the problem of forecasting GDP and inflation using quarterly U.S. data on 162 time ...
Working Paper
Technical note on \"assessing Bayesian model comparison in small samples\"
This technical note is developed as a companion to the paper ?Assessing Bayesian Model Comparison in Small Samples? (Globalization and Monetary Policy Institute working paper no. 189). Taking the workhorse open-economy model of Martnez-Garca and Wynne (2010) with nominal rigidities under monopolistic competition as our Data-Generating Process, we investigate with simulated data how Bayesian model comparison based on posterior odds performs when the model becomes arbitrarily close to a closed-economy and/or an economy with flexible prices and perfect competition. This technical note elaborates ...
Working Paper
Commodity Exports, Financial Frictions and International Spillovers
This paper offers a solution to the international co-movement puzzle found in open-economy macroeconomic models. We develop a small open-economy (SOE) dynamic stochastic general equilibrium (DSGE) model describing three endogenous channels that capture spillovers from the world to a commodity exporter: a world commodity price channel, a domestic commodity supply channel and a financial channel. We estimate our model with Bayesian methods on two commodity-exporting SOEs, namely Canada and South Africa. In addition to explaining international business cycle synchronization, the new model ...
Working Paper
Uniform Priors for Impulse Responses
There has been a call for caution when using the conventional method for Bayesian inference in set-identified structural vector autoregressions on the grounds that the uniform prior over the set of orthogonal matrices could be nonuniform for individual impulse responses or other quantity of interest. This paper challenges this call by formally showing that, when the focus is on joint inference, the uniform prior over the set of orthogonal matrices is not only sufficient but also necessary for inference based on a uniform joint prior distribution over the identified set for the vector of ...