I want to incorporate spatial information (e.g. the spatial matrix) into the prior information in Bayesian VAR (BVAR).
Intuitively, the comovements of the dependent variables in the VAR system are not identical, but neighborhood locations are more influential on average. I want a prior to represent this belief.
Combining spatial information (neighboring relationship) into BVAR is not new. In the paper below, the spatial prior is modified based on Minnesota prior. I want to replicate the results.
Dowd, M. R., & Lesage, J. P. (1997). Analysis of spatial contiguity influences on state price level formation. International Journal of Forecasting, 13(2), 245-253. doi:10.1016/s0169-2070(96)00714-5
I use EViews 10. I find after choosing BVAR and Minnesota prior, instead of setting hyperparameters, I can see prior specification --> user define . I guess it may be a hopeful way to the goal. Can you give an example? I have checked the user guide, but no example for the user-defined specification. Thank you.
Ren
User defined Minnesota prior Bayesian VAR (BVAR) in Eviews 10
Moderators: EViews Gareth, EViews Moderator
Who is online
Users browsing this forum: No registered users and 37 guests