Estimating time variation in measurement error from data revisions: an application to backcasting and forecasting in dynamic models

George Kapetanios*, Tony Yates

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)

4 Citations (Scopus)

Abstract

Over time, economic statistics are refined. This implies that data measuring recent economic events are typically less reliable than older data. Such time variation in measurement error affects optimal forecasts. Measurement error, and its time variation, are of course unobserved. Our contribution is to show how estimates of these can be recovered from the variance of revisions to data using a behavioural model of the statistics agency. We illustrate the gains in forecasting performance from exploiting these estimates using a real-time dataset on UK aggregate expenditure data. Copyright (C) 2009 John Wiley & Sons, Ltd.

Original languageEnglish
Pages (from-to)869-893
Number of pages25
JournalJournal of Applied Econometrics
Volume25
Issue number5
Early online date28 Sep 2009
DOIs
Publication statusPublished - Aug 2010

Keywords

  • REAL-TIME
  • MONETARY-POLICY
  • DATA SET

Cite this