Are more data always better for factor analysis? Results for the euro area, the six largest euro area countries and the UK

Giovanni Caggiano, George Kapetanios, Vincent Labhard

Research output: Contribution to journalArticleResearchpeer-review

28 Citations (Scopus)

Abstract

Factor-based forecasting has been at the forefront of developments in the macroeconometric forecasting literature in the recent past. Despite the flurry of activity in the area, a number of specification issues such as the choice of the number of factors in the forecasting regression, the benefits of combining factor-based forecasts and the choice of the dataset from which to extract the factors remain partly unaddressed. This paper provides a comprehensive empirical investigation of these issues using data for the euro area, the six largest euro area countries, and the UK.

Original languageEnglish
Pages (from-to)736-752
Number of pages17
JournalJournal of Forecasting
Volume30
Issue number8
DOIs
Publication statusPublished - Dec 2011
Externally publishedYes

Keywords

  • factors
  • forecast combinations
  • large datasets

Cite this