 |
 |
Dear all, not long ago I started working with WinBUGS and within that espeacially the car.proper model. I have a linear mixed model with random effects u which are correlated and jointly normal distributed. So far I just copy-pasted examples which looked like u[1:k]~car.proper(mu[] ,C[] , adj[] ,num[] ,m[] , tau ,gamma) gamma.min <- min.bound(C[], adj[], num[], m[]) gamma.max <- max.bound(C[], adj[], num[], m[]) gamma ~ dunif(gamma.min, gamma.max) Like I understood the gamma represents the degree of spatial dependence. I would like to estimate it. As a start I just took a mean of the monitored gammas (I'm only monitoring the u's and gamma). This gave me no good estimation. Since I am not that deep into the program my idea was simply that this problem might be due to the uniform distribution. Maybe a truncated normal with the latter gamma as mean might be a better idea? I am thankful for any recommendation. Best wishes Beate Weidenhammer -- Beate Weidenhammer wiss. Mitarbeiterin Freie Universität Berlin Fachbereich Wirtschaftswissenschaft Institut für Statistik und Ökonometrie Lehrstuhl Rendtel Garystr. 21 (Raum 325) D-14195 Berlin Tel.: +49 30 838-54203 Fax: +49 30 838-456629 email: [log in to unmask] ------------------------------------------------------------------- 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