• Medientyp: E-Book
  • Titel: Combining large numbers of density predictions with Bayesian predictive synthesis
  • Beteiligte: Chernis, Tony [Verfasser:in]
  • Erschienen: [Ottawa]: Bank of Canada, [2023]
  • Erschienen in: Bank of Canada: Staff working paper ; 2023,45
  • Ausgabe: Last updated: August 21, 2023
  • Umfang: 1 Online-Ressource (circa 46 Seiten); Illustrationen
  • Sprache: Englisch
  • DOI: 10.34989/swp-2023-45
  • Identifikator:
  • Schlagwörter: Econometric and statistical methods ; Graue Literatur
  • Entstehung:
  • Anmerkungen:
  • Beschreibung: Bayesian predictive synthesis is a flexible method of combining density predictions. The flexibility comes from the ability to choose an arbitrary synthesis function to combine predictions. I study the choice of synthesis function when combining large numbers of predictions-a common occurrence in macroeconomics. Estimating combination weights with many predictions is difficult, so I consider shrinkage priors and factor modelling techniques to address this problem. The dense weights of factor modelling provide an interesting contrast with the sparse weights implied by shrinkage priors. I find that the sparse weights of shrinkage priors perform well across exercises.
  • Zugangsstatus: Freier Zugang