Time Varying Dimension Models

Joshua C.C. Chan, Gary Koop, Roberto Leon-Gonzalez, Rodney W. Strachan

Research output: Working paperDiscussion paper

4 Downloads (Pure)

Abstract

Time varying parameter (TVP) models have enjoyed an increasing popularity in empirical macroeconomics. However, TVP models are parameter-rich and risk over-fitting unless the dimension of the model is small. Motivated by this worry, this paper proposes several Time Varying dimension (TVD) models where the dimension of the model can change over time, allowing for the model to automatically choose a more parsimonious TVP representation, or to switch between different parsimonious representations. Our TVD models all fall in the category of dynamic mixture models. We discuss the properties of these models and present methods for Bayesian inference. An application involving US inflation forecasting illustrates and compares the different TVD models. We find our TVD approaches exhibit better forecasting performance than several standard benchmarks and shrink towards parsimonious specifications.
Original languageEnglish
Place of PublicationGlasgow
PublisherUniversity of Strathclyde
Pages1-33
Number of pages34
Volume2011
Publication statusPublished - 11 May 2011

Keywords

  • time varying parameter
  • TVP
  • time varying dimension
  • TVD
  • bayesian inference

Fingerprint Dive into the research topics of 'Time Varying Dimension Models'. Together they form a unique fingerprint.

  • Cite this

    Chan, J. C. C., Koop, G., Leon-Gonzalez, R., & Strachan, R. W. (2011). Time Varying Dimension Models. (16 ed.) (pp. 1-33). University of Strathclyde.