R help - Mar 2013 - using dlmModPoly in library dlm

Hi Group,

I'm trying to build a model to predict a product's sale price. I'm
researching the dlm package. Looks like I should use dlmModPoly, dlmMLE,
dlmFilter, dlmSmooth, and finally dlmForecast. I'm looking at the Nile
River example and I have a few questions:

   1.

   If I only want to predict future sale price based on observed sale
   price, I should use a univariate model, correct?
   2.

   how do I initiate value for dV and dW? In the example code:
   dlmModPoly(1, dV = exp(par[1]), dW = exp(par[2])) Why dV and dW was
   initiated that way?
   3.

   I'm not sure how to read output of dlmForecast. f is matrix of expected
   values of future observations. new Obs is list of matrices containing the
   simulated future values of the observations. Should I take f as the
   forecast result? Or new Obs?
   4.

   In my experiment, f (output from dlmForecast) has all 0s. And I have
   huge variance like 10016568. Does that mean my result is not valid?

Thanks a lot for any insights!

Hua

	[[alternative HTML version deleted]]