Many thanks to all responders. It turns out that there is a winbugs
update available, which defines a new version of inprod, inprod2.
Using inprod2 the vectorized code runs in about the same time as the
scalar version.
On the print problem: the issue here turns out to be that the arm
I remember having similar problem with inprod function. As far as I could
remember a sole deference in my models was that I used inprod instead of
explicit sum (exactly as you did). In my case the inprod version was faster but
result were completely aberrant. So I abandoned the inprod as
I'm new to bugs, so please bear with me. Can someone tell me if the
following two models are doing the same thing? The reason I ask is
that with the same data, the first (based on 4 separate coeffs
a1--a4) takes about 50 secs, while the second (based on a vectorized
form, a[]) takes about
Philip A. Viton wrote:
I'm new to bugs, so please bear with me. Can someone tell me if the
following two models are doing the same thing? The reason I ask is
that with the same data, the first (based on 4 separate coeffs
a1--a4) takes about 50 secs, while the second (based on a
Philip,
If you are using WinBUGS 1.4, then the poor performance of the
inprod function is a known problem. An inprod2 function
was introduced in 1.4.3 to improve performance. See
http://www.mrc-bsu.cam.ac.uk/bugs/winbugs/contents.shtml#problems
You might try using that.
For WinBUGS problems,
5 matches
Mail list logo
