Displaying 3 results from an estimated 3 matches for "prior2".
Did you mean:
prior
2011 Feb 17
0
Multi-response MCMCglmm (gaussian and zapoisson)
...the differences between the zero-altered regression coefficients and the Poisson regression coefficients. This allows identification of zero-inflation or zero-deflation in response to the explanatory variables.
I therefore fit an additional model for the zapoisson response only, looking like this:
prior2<-list(R=list(V=diag(1)/4,nu=0.002),G=list(G1=list(V=diag(1)/4,nu=0.002),G2=list(V=diag(1)/4,nu=0.002),G3=list(V=diag(1)/4,nu=0.002)))
m2<-MCMCglmm(fixed=resp3 ~
trait:(expl1 + expl2+ expl3+ expl4+ expl5?.)+trait,
random=~trait:rand1+trait: rand1: rand2+ trait: rand1: rand2: rand3,
rcov=~tra...
2012 May 02
0
MCMCglmm priors including phylogeny
...) ~ trait:Ecotype - 1,
random=~us(trait):animal, rcov=~us(trait):units, family=c("gaussian","gaussian"),
prior=prior1, data=meandata, pedigree=meantree, nodes="TIPS",
thin=100, nitt=150000, burnin=30000, verbose=F)
#prior model2
prior2<-list(R = list(V = diag(2)*x, n=2))
#model2
m2<-MCMCglmm(cbind(reac.prob.logit,inert.prob.logit) ~ trait:Ecotype - 1,
rcov=~us(trait):units, family=c("gaussian","gaussian"),
prior=prior2, data=meandata,
thin=100, nitt=150000, burni...
2011 Apr 19
0
Error message in package:bayesSurv. Why?
...a=Surv(childtime+.01,childevent)~nchild+cluster(id),
random=~1,
formula2=Surv(mddtime+.01,mddevent)~nchild+blustatus+well.before+earlydep+cluster(id),
random2=~1,
onlyX=FALSE,
dir="chaindir.childmdd", nsimul=nsimul.childmdd,
prior=prior.gspl.child, prior2=prior.gspl.mdd,
prior.beta=prior.beta.child, prior.beta2=prior.beta.mdd,
prior.b=prior.b.child, prior.b2=prior.b.mdd,
init=init.child, init2=init.mdd,
store=list(a=TRUE, a2=TRUE, a.b=TRUE, a.b2=TRUE),
data=dataset3long)
This seems to run quite happily (the +...