Re: [R] Baysian model averaging method

From: Spencer Graves <>
Date: Sun 12 Feb 2006 - 21:25:24 EST

          I'm not certain what you are asking. Do you want to fit a time series model using Bayesian Model Averaging (BMA), or do you want to predictions with confidence intervals from a BMA fit or both? For any of these, I suggest you start with the posting guide! "" and with "RSiteSearch" in particular. I just got 31 hits from 'RSiteSearch("Baysian model averaging")', which included discussions of the BMA and ensembleBMA packages as well as an article on "BMA: An R package for Bayesian Model Averaging" by Raferty, Painter and Volinsky, 3 of the 4 authors of the BMA package.

          I couldn't find a function for a BMA time series fit. If I wanted that, I'd probably start by asking the maintainers for "BMA" and "ensembleBMA" (cc'ed on this reply) and by reading the code for the nearest things I could find. I'd make local copies of one or more functions and try to walk through the code line by line until I thought I understood it well enough to modify it to do what I wanted. With luck, someone may reply to this email with hints or even code that might make that task easier.

	  hope this helps,
	  spencer graves

p.s. If I had understood your question better, I might have been able to supply more useful suggestions.

anil kumar rohilla wrote:
> HI, List
> I want to know weather any body has used BMA Package for model
averaging for prediction of future values.....What are the paprmeters we have to suplly to the model. Any script for the same.
> thanks in advance
> PUNE-411005 INDIA
> MOBILE +919422023277
> [[alternative HTML version deleted]]
> ______________________________________________
> mailing list
> PLEASE do read the posting guide! mailing list PLEASE do read the posting guide! Received on Sun Feb 12 21:28:26 2006

This archive was generated by hypermail 2.1.8 : Tue 14 Feb 2006 - 00:42:54 EST