A theme of much recent empirical work on inflation forecasting is that the judicious
pooling of information from a large number of indicators provides the best approach to
predicting inflation. One method that has been particularly promising is to simply
average the forecasts from a large number of models, each of which has a single predictor
variable. In this paper, I have considered instead using Bayesian Model Averaging for
U.S. inflation forecasting and found that it fairly consistently outperforms this equal
weighted forecast averaging. This result is consistent across different subperiods and
across different inflation measures