Bayesian Model Selection with an Uninformative Prior
Bayesian model selection with posterior probabilities and no subjective prior information is generally not possible due to the Bayes factors being ill-defined. Using careful consideration of the parameter of interest in cointegration analysis and a respecifcation of the triangular model of Phillips (1991), this paper presents an approach that allows for Bayesian comparison of models of cointegration with ‘ignorance’ priors. Using the concept of Stiefel and Grassman manifolds, diffuse priors are specified on dimension and direction of the cointegrating space. The approach is illustrated using a simple term structure of interest rates model.
|Date of creation:||Jan 2004|
|Date of revision:|
|Publication status:||Published in Oxford Bulletin of Economics and Statistics, Volume 65, Supplement 1, December 2003, pp. 863-876. [ doi:10.1046/j.0305-9049.2003.00095.x ]|
|Contact details of provider:|| Postal: |
Phone: +44 (0)1782 584581
Fax: +44 (0)1782 717577
Web page: http://www.keele.ac.uk/depts/ec/cer/
More information through EDIRC
|Order Information:|| Postal: Centre for Economic Research, Research Institute for Public Policy and Management, Keele University, Staffordshire ST5 5BG - United Kingdom|
Web: http://www.keele.ac.uk/depts/ec/cer/pubs_kerps.htm Email:
When requesting a correction, please mention this item's handle: RePEc:kee:kerpuk:2004/01. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Martin E. Diedrich)
If references are entirely missing, you can add them using this form.