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.
