Estimating the Output, Inflation and Unemployment Gaps in Ireland using Bayesian Model Averaging

Abstract

We aim to overcome the issue of model selection in output, wage inflation and unemployment gap estimation for Ireland, using Bayesian model averaging. Employing a stochastic model specification search with time-varying parameters approach, we draw from a number of standard model specifications, based on variable selection, trend output identification and distributional assumptions. From the resulting model averaging with Irish data, we find that the unemployment gap is a strong predictor of the output gap, but conditional on the unemployment gap, the output gap has limited influence on the wage inflation gap. Additionally, we observe a decline in potential output growth from the early 2000s, although growth rates have increased strongly since Q1 2012. Finally we find that shocks to output growth and wage inflation are better characterised by Student’s t-distributions, rather than conventional Gaussian distributions, suggesting that extreme events occur with a more relative frequency that is typically assumed.