Forecasting inflation : the use of dynamic factor analysis and nonlinear combinations

Loading...
Thumbnail Image

Date

Authors

Hall, Stephen George
Tavlas, George S.
Wang, Yongli

Journal Title

Journal ISSN

Volume Title

Publisher

Wiley

Abstract

This paper considers the problem of forecasting inflation in the United States, the euro area, and the United Kingdom in the presence of possible structural breaks and changing parameters. We examine a range of moving window techniques that have been proposed in the literature. We extend previous works by considering factor models using principal components and dynamic factors. We then consider the use of forecast combinations with time-varying weights. Our basic finding is that moving windows do not produce a clear benefit to forecasting. Time-varying combination of forecasts does produce a substantial improvement in forecasting accuracy.

Description

DATA AVAILABILITY STATEMENT : All data are taken from publicly available data sources as defined in the data appendix. The particular vintage of data used in this study is available upon request from the authors.

Keywords

Dynamic factor models, Forecast combinations, Kalman filter, Rolling windows, Structural breaks, SDG-08: Decent work and economic growth

Sustainable Development Goals

Citation

Hall, S. G., Tavlas, G. S.,& Wang, Y. (2023). Forecasting inflation: The useof dynamic factor analysis and nonlinearcombinations.Journal of Forecasting,42(3),514–529.https://doi.org/10.1002/for.2948.