Bayesian vector autoregressive models for modeling inflation rate in Nigeria

Abstract

This study focused on the Bayesian approach to the estimation of Vector Autoregressive (VAR) model using data on inflation rates in Nigeria. This method allows a combination of prior information and data information .The study provides a description of inflation rates in Nigeria using six different Bayesian VAR priors (diffuse prior, Minnesota prior, natural conjugate prior, independent normal Wishart prior, stochastic search variable selection prior-Wishart and stochastic search variable selection prior-VAR). The performance of various models was evaluated using root mean square error (RMSE). The stochastic search variable selection-Wishart out performs other methods. The impulse response function was estimated. The study concludes that stochastic search variable selection prior-Wishart is the best of all the Bayesian VAR prior to model inflation rate in Nigeria.