I have written some WinBUGS code to produce simple forecast
values:
for(i in 1 :T){
y[i]~dnorm(mu[i],tau)
mu.data1[i] <- beta[0] + beta[1]*x[i]
}
for(j in (T+1):(T+3)){
mu.data1[j] <- beta[0] + beta[1]*x[j]
}
These forecasted time-series values correspond to time-series
values in another, different, dataset with known mu.data2[j].
This second dataset is known to be biased and I would like to
estimate its bias by calibrating it using the forecasted values.
The means are approximately normally distributed. When I
tried:
for(j in (T+1):(T+3)){
mu.data1[j] <- a + b[j]*mu.data2[j]
}
WinBUGS of course told me that I had defined my mu.data1 node
twice! I then proceeded to take the posterior distributions for
the mu.data1[i] forecasted values, and I fitted normal
distributions to them to try to use them as priors in another
set of code:
for(i in 1:3){
mu.data1[i] <- a + b[i]*mu.data2[i+T]
}
#priors
mu.data[1] ~ dnorm(...)
mu.data[2] ~ dnorm(...)
mu.data[3] ~ dnorm(...)
When I try to do this, WinBUGS gives me the strangest errors,
telling me that I need extra parentheses in places that don't
need them, etc.
If anyone could offer suggestions as to how to use the
forecasted values in future bias-estimation calculations, it
would be greatly appreciated.
Sincerely,
david paul
__________________________________________________
Do You Yahoo!?
Yahoo! Tax Center - online filing with TurboTax
http://taxes.yahoo.com/
-------------------------------------------------------------------
This list is for discussion of modelling issues and the BUGS software.
For help with crashes and error messages, first mail [log in to unmask]
To mail the BUGS list, mail to [log in to unmask]
Before mailing, please check the archive at www.jiscmail.ac.uk/lists/bugs.html
Please do not mail attachments to the list.
To leave the BUGS list, send LEAVE BUGS to [log in to unmask]
If this fails, mail [log in to unmask], NOT the whole list
|