A BVAR MODEL FOR FORECASTING PARAGUAY’S
INFLATION RATE IN TURBULENT MACROECONOMIC ENVIRONMENTS
VICENTE RIOS IBÁÑEZ*
Msc. Macroeconomic Policy and Financial Markets (BGSE)
BANCO CENTRAL DEL PARAGUAY
DOCUMENTOS DE TRABAJO
DEPARTAMENTO DE SÍNTESIS MACROECONÓMICA E INVESTIGACIÓN
January 2011
Se agradecen los consejos, opiniones y ayuda prestada por los compañeros Gustavo Biedermann, Victor Ruiz y Dario Rojas Las opiniones y resultados expuestos en este documento, son de exclusiva responsabilidad del autor y no comprometen la posición institucional del Banco Central del Paraguay.
ABSTRACT
In this research I explore the methodology of Bayesian autoregressive methods to forecast inflation and other macroeconomic time series of interest. I estimate a Bayesian vector of autoregressive model to forecast inflation, GDP and the interest rate of Paraguay taking as main approach the Minnesota prior methodology developed by R.B. Litterman (1984). The main out of sample accuracy statistics, the RMSFE and U-Theil statistic results show that in the 75% of the subsamples of forecast characterized as turbulent macro environments, Bayesian specifications outperform traditional VAR models in terms of accuracy. When using quarterly data Bayesian techniques deliver also more accurate forecasts than VAR models ones.
INTRODUCTION
In this research I study Bayesian inference methods in order to contribute to Paraguayan Central Bank monetary policy forecasts and to the growing literature of Bayesian forecasting. The basic idea here is that given the scarcity of data to forecast macroeconomic time series with common unrestricted vector of autoregressive (UVARs), priors about the probabilistic density of the parameters of interest can be used to outperform the original UVAR models in terms of accuracy as in Koop and Korobilis (2010). In particular what I do is to compare the accuracy of the forecast results of Minnesota Prior elicitation approach in a BVAR modelling environment versus the results obtained with a VAR using the RMSFE as measure to determine whether should be preferable to forecast with Bayesian vector of autoregressive models (BVAR). The main finding of this paper is that Bayesian techniques improve the performance of traditional VAR models in the 75% of turbulent subsamples used to check forecast accuracy.
A BVAR model for forecasting Paraguay’s Inflation rate in turbulent macroeconomic environments - BCP - Port... by portalguarani
Fuente: BANCO CENTRAL DEL PARAGUAY
LIBRO DIGITAL
Fuente digital: http://www.bcp.gov.py
Registro: Setiembre 2011
|