حصان حیدری

This paper investigates the use of different priors to improve the inflation forecasting performance of BVAR models with Litterman’s prior. A Quasi-Bayesian method, with several different priors, is applied to a VAR model of the Iranian economy from 1981:Q2 to 2007:Q1. A novel feature with this paper is the use of g-prior in the BVAR models to alleviate poor estimation of drift parameters of Traditional BVAR models. Some results are as follows: (1) our results show that in the Quasi-Bayesian framework, BVAR models with Normal-Wishart prior provides the most accurate forecasts of Iranian inflation; (2) The results also show that generally in the parsimonious models, the BVAR with g-prior performs better than BVAR with Litterman’s prior.

This paper focuses on the development of modern non-structural dynamic multivariate time series models and evaluating performance of various alternative specifications of these models for forecasting Iranian inflation. The Quasi-Bayesian method, with Literman prior, is applied to Vector autoregressive (VAR) model of the Iranian economy from 1981:Q2 to 2006:Q1 to assess the forecasting performance of different models over different forecasting horizons. The Bewley transformation is also employed for the re-parameterization of the VAR models to impose the mean of the change of inflation to zero. Applying the Bewley (1979) transformation to force the drift parameter of change of inflation to zero in the VAR model improves forecast accuracy in comparison to the traditional BVAR.