Working Papers,
National Institute of Economic Research

Abstract: In this paper, we investigate whether the two main consumer confidence indicators available for Sweden – that of the National Institute of Economic Research and that of the European Commission – can nowcast Swedish household consumption expenditure. In a simulated out-of sample nowcast exercise, we find that the consumer confidence indicator of the National Institute of Economic Research appears most useful for this purpose. The root mean square error of the nowcast from the model employing this indicator is the lowest of all the studied models which rely on survey data. The nowcasting performance of the model using the consumer confidence indicator of the European Commission is less impressive; while it outperforms the simplest possible benchmark model, its root mean square error is considerably higher than that of the model relying on the consumer confidence indicator of the National Institute of Economic Research. An implication of our findings is that while the European Commission’s survey programme may have been successful in creating a set of harmonised data for the member countries of the European Union, it is not obvious that the harmonised indicators are the most relevant ones for analysis, nowcasting or forecasting in each country.

Keywords: Household consumption; Nowcasting

JEL-codes: E21; E27

16 pages, September 1, 2015

Full text files

Working-Paper-139-Do...e-Intended-to-Do.pdf  

Download statistics

• National Institute of Economic Research
• Home page for this series

Questions (including download problems) about the papers in this series should be directed to Sarah Hegardt Grant ()
Report other problems with accessing this service to Sune Karlsson ().

This page generated on 2024-02-05 17:12:55.