Email discussion lists for the UK Education and Research communities

BUGS@JISCMAIL.AC.UK

View:

 Message: [ First | Previous | Next | Last ] By Topic: [ First | Previous | Next | Last ] By Author: [ First | Previous | Next | Last ] Font: Proportional Font
 LISTSERV Archives BUGS Home BUGS 2006

Options

Subject:

Re: Discrete uniform with missing values

From:

Date:

Thu, 19 Oct 2006 10:30:55 +0100

Content-Type:

text/plain

Parts/Attachments:

 text/plain (66 lines)
 ```Hi, Many thanks to everyone (Andrew Millard, David LeBlond, Simon Bonner, George Tomlinson, Bob O'Hara, Andrew Thomas, Nicky Best, Samu Mantyniemi, Mark Brewer, David Spiegelhalter & Rodney Sparapani) who pointed out that I had used the dcat function incorrectly, and that the correct usage in this context would be: model{ for(j in 1:12){ p[j] <- 1/12 } for(i in 1:n){ x[i] ~dcat(p[]) } } DATA list(n=2,x=c(1,NA)) I found that this modified version worked fine. David LeBlond also suggested that it should be possible to solve the problem using dmulti. Best wishes, Adam > Hi, > I am interested in assigning a discrete uniform distribution to a > variable x in BUGS. This is a variable for which I usually have data, > but for which the data are sometimes missing. The variable can take > integer values between 1 and 12. > > My initial idea was to model my variable using the dcat function, e.g. > with > for (j in 1:n ) { > p[j] <- 1 / 12 > x[j] ~ dcat(p[j]) > }, > but this produces an error message of the form > > error for node x[1] of type GraphCat.StdNode node invalid integer > value given > apparently because it is not possible to use dcat with missing data. > > The next idea was to use: for ( j in 1:n ) { > x[j] <- round(x.cont[j]) > x.cont[j] ~ dunif(0.5, 12.5) > } > but when I compile this model it (rightly) produces an error message > to say that x[1] has been defined more than once. > > Does anyone know if there is a way of doing this within BUGS...? > Many thanks, Adam > -- Dr. Adam Butler Postdoctoral Research Statistician Biomathematics & Statistics Scotland The King's Buildings, Edinburgh EH9 3JZ, UK Tel: +44(0)131 650 4896 Fax: +44(0)131 650 4901 ------------------------------------------------------------------- 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 ```