Hi Andrew,
I realized my very silly mistake very quickly after hitting the "send"
button! My apologies to you, to all the great people behind the program,
and to fellow users I have inadvertently spooked!
Best wishes,
Y M
-----Original Message-----
From: Thomas, Andrew [mailto:[log in to unmask]]
Sent: Wednesday, April 16, 2003 12:24 AM
To: 'Y M Thum '
Subject: RE: step function clarification
Hello I do not see your problem. I monitor yes[] and then do 1000 updates
and then do CODA to look at the values of yes[]. I only see 0.0 and 1.0. (I
have not looked at each of the 20000 numbers but...) If you look at the
graphical output trace or history plots you will see the line jumping from
0.0 to 1.0 every few iterations which looks a bit of a mess. Could you give
me more details of what you found.
Regards
Andrew
-----Original Message-----
From: Y M Thum
To: [log in to unmask]
Sent: 15/04/2003 15:21
Subject: step function clarification
Friends:
I have been using step() (winbugs 1.3) with confidence until I noticed
that
step(a-b) does not always return a "1" or a "0". For "yes[i]" below
I need instead to use step(step(a-b)), which is in "altight[i]".
Any clarifications will most welcome!
Thanks much.
Y M
p.s. Please respond directly to [log in to unmask]
------------------------------------------------------
model {
for(i in 1:20) {
y[i] ~ dbern(mu.p[i]);
mu.p[i] <- p;
yes[i] <- step(mu.p[i] - .5);
alright[i] <- step(yes[i]);
}
p ~ dunif(0,1);
}
Data:
list(y=c(1,1,1,1,1,0,0,0,0,1,1,1,1,1,1,0,0,0,0,1))
------------------------------------------------------
-------------------------------------------------------------------
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
-------------------------------------------------------------------
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
|