Evaluating the use of real-time data in forecasting output levels and recessionary events in the US

The paper proposes a modelling framework and evaluation procedure to judge the usefulness of real-time datasets incorporating past data vintages and survey expectations in forecasting. The analysis is based on `meta models' obtained using model-averaging techniques and judged by various statist...

Full description

Bibliographic Details
Main Authors: Aristidou, Chrystalleni, Lee, Kevin, Shields, Kalvinder
Format: Article
Language:English
Published: Wiley 2018
Subjects:
Online Access:https://eprints.nottingham.ac.uk/51050/
_version_ 1848798401610645504
author Aristidou, Chrystalleni
Lee, Kevin
Shields, Kalvinder
author_facet Aristidou, Chrystalleni
Lee, Kevin
Shields, Kalvinder
author_sort Aristidou, Chrystalleni
building Nottingham Research Data Repository
collection Online Access
description The paper proposes a modelling framework and evaluation procedure to judge the usefulness of real-time datasets incorporating past data vintages and survey expectations in forecasting. The analysis is based on `meta models' obtained using model-averaging techniques and judged by various statistical and economic criteria, including a novel criterion based on a fair bet. Analysing US output data over 1968q4-2015q1, we find both elements of the real-time data are useful with their contributions varying over time. Revisions data are particularly valuable for point and density forecasts of growth but survey expectations are important in forecasting rare recessionary events.
first_indexed 2025-11-14T20:19:11Z
format Article
id nottingham-51050
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:19:11Z
publishDate 2018
publisher Wiley
recordtype eprints
repository_type Digital Repository
spelling nottingham-510502019-04-22T04:30:12Z https://eprints.nottingham.ac.uk/51050/ Evaluating the use of real-time data in forecasting output levels and recessionary events in the US Aristidou, Chrystalleni Lee, Kevin Shields, Kalvinder The paper proposes a modelling framework and evaluation procedure to judge the usefulness of real-time datasets incorporating past data vintages and survey expectations in forecasting. The analysis is based on `meta models' obtained using model-averaging techniques and judged by various statistical and economic criteria, including a novel criterion based on a fair bet. Analysing US output data over 1968q4-2015q1, we find both elements of the real-time data are useful with their contributions varying over time. Revisions data are particularly valuable for point and density forecasts of growth but survey expectations are important in forecasting rare recessionary events. Wiley 2018-04-22 Article PeerReviewed application/pdf en https://eprints.nottingham.ac.uk/51050/1/nowevaluation%202018%201%2023%20Jan%20final%20submission.pdf Aristidou, Chrystalleni, Lee, Kevin and Shields, Kalvinder (2018) Evaluating the use of real-time data in forecasting output levels and recessionary events in the US. Journal of the Royal Statistical Society: Series A (Statistics in Society) . ISSN 1467-985X Real-time data; Revision; Survey; Forecasting; Model averaging; Output; Recession https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/rssa.12366 doi:10.1111/rssa.12366 doi:10.1111/rssa.12366
spellingShingle Real-time data; Revision; Survey; Forecasting; Model averaging; Output; Recession
Aristidou, Chrystalleni
Lee, Kevin
Shields, Kalvinder
Evaluating the use of real-time data in forecasting output levels and recessionary events in the US
title Evaluating the use of real-time data in forecasting output levels and recessionary events in the US
title_full Evaluating the use of real-time data in forecasting output levels and recessionary events in the US
title_fullStr Evaluating the use of real-time data in forecasting output levels and recessionary events in the US
title_full_unstemmed Evaluating the use of real-time data in forecasting output levels and recessionary events in the US
title_short Evaluating the use of real-time data in forecasting output levels and recessionary events in the US
title_sort evaluating the use of real-time data in forecasting output levels and recessionary events in the us
topic Real-time data; Revision; Survey; Forecasting; Model averaging; Output; Recession
url https://eprints.nottingham.ac.uk/51050/
https://eprints.nottingham.ac.uk/51050/
https://eprints.nottingham.ac.uk/51050/