Forecasting US Inflation Using Bayesian Nonparametric Models

The relationship between inflation and predictors such as unemployment is potentially nonlinear with a strength that varies over time, prediction errors error may be subject to large, asymmetric shocks. Inspired by these concerns, we develop model for forecasting nonparametric both in the conditional mean using Gaussian Dirichlet processes, respectively. We discuss how features important producing accurate forecasts of inflation. In exercise involving CPI inflation, find our approach has substantial benefits, overall left tail, modeling being particular importance.