Abstract/Summary

How do professionals forecast in uncertain times, when the relationships between variables that held in the past may no longer be useful for forecasting the future? For inflation forecasting, we answer this question by measuring survey respondents’ adherence to their pre-COVID-19 Phillips curve models during the pandemic. We also ask whether professionals ought to have put their trust in their Phillips curve models over the COVID-19 period. We address these questions allowing for heterogeneity in respondents’ forecasts, and in their perceptions of the Phillips curve relationship.