A VAR Framework for Forecasting Hong Kong'S Output and Inflation

Hans Genberg and Jian Chang ()
Additional contact information
Jian Chang: Research Department, Hong Kong Monetary Authority

No 702, Working Papers from Hong Kong Monetary Authority

Abstract: This paper develops a multivariate time series model to forecast output growth and inflation in the Hong Kong economy. We illustrate the steps involved in designing and building a vector autoregression (VAR) forecasting model, and consider three types of VAR models, including unrestricted, Bayesian and conditional VARs. Our findings suggest that the Bayesian VAR framework incorporating external influences provide a useful tool to produce more accurate forecasts relative to the unrestricted VARs and univariate time series models, and conditional forecasts have the potential to further improve upon the Bayesian models. In particular, a six-variable Bayesian VAR including domestic output, domestic inflation, domestic investment, world GDP, the best lending rate, and import prices appears to generate good out-of-sample forecasts results.

Keywords: VAR and BVAR models; conditional forecasts; forecasting; model evaluation (search for similar items in EconPapers)
JEL-codes: C52 C53 E37 (search for similar items in EconPapers)
Pages: 25 pages
Date: 2007-03
New Economics Papers: this item is included in nep-cba, nep-for and nep-mac
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.info.gov.hk/hkma/eng/research/working/pdf/HKMAWP07_02_full.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hkg:wpaper:0702

Access Statistics for this paper

More papers in Working Papers from Hong Kong Monetary Authority Contact information at EDIRC.
Bibliographic data for series maintained by Simon Chan ( this e-mail address is bad, please contact ).