This paper provides a comprehensive analysis of the forecastability of the real price of natural gas in the United States at the monthly frequency considering a universe of models that differ in their complexity and economic content. Our key finding is that considerable reductions in mean-squared prediction error relative to a random walk benchmark can be achieved in real time for forecast horizons of up to two years. A particularly promising model is a six-variable Bayesian vector autoregressive model that includes the fundamental determinants of the supply and demand for natural gas. To capture real-time data constraints of these and other predictor variables, we assemble a rich database of historical vintages from multiple sources. We also compare our model-based forecasts to readily available model-free forecasts provided by experts and futures markets. Given that no single forecasting method dominates all others, we explore the usefulness of pooling forecasts and find that combining forecasts from individual models selected in real time based on their most recent performance delivers the most accurate forecasts.

Amiti et al. (2024) seek to answer a very topical and important research question: How much did supply-side disruptions and the tight labor market contribute to the recent surge in inflation? The answer provided by the authors is: about 2 percentage points. To arrive at their answer, the authors use a calibrated two-sector New Keynesian model in which they use three correlated shocks in a perfect-storm type setting. The paper also has an interesting empirical part that provides evidence that the channels emphasized in the theoretical model are at work in the data.

The female labor income share update is based on the methodology by Neef and Robilliard (2022). This update provides estimates of the female labor income share for 1990 –2023. This methodological note explains the data sources and methodology in detail, highlighting data availability and new data that was incorporated.