铤而走险 发表于 2012-4-29 10:23 
您好!很抱歉又要打扰您!
按照您的模型运行后,调出Winbugs运行时还是没有参数估计出来,问题还是那样! ...
library(R2WinBUGS)
y<-read.table("
D:/Bugs/jump.txt") #import data#
y=y[,1]
t=length(y)
y=100*(log(y[2:t])-log(y[1:(t-1)]))
N<-length(y)
Xi0<-rep(0,N) # Give initial values to state variables#
J0<-rep(0,N)
data<-list("N","y")
# Give initial values to the parameters for winbugs #
inits <-function() {list ( tau=2,
Jtau=2,
mu=0,
Jmu=0,
lamda = 0.05, Xi=Xi0,J=J0)}
parameters<- c("Sigma","JSigma","mu","Jmu","lamda","Xi","J")
jump.sim<-bugs (data, inits=inits, parameters, "model.bug", n.chains=1, n.thin=1,
n.iter=10000,n.burnin=5000,debug=TRUE,DIC=TRUE,
bugs.directory = "D:/WinBUGS14/",working.directory = "D:/Bugs")
attach.bugs(jump.sim)
print(jump.sim,digits=4)
#################
Inference for Bugs model at "model.bug", fit using WinBUGS,
1 chains, each with 10000 iterations (first 5000 discarded)
n.sims = 5000 iterations saved
mean sd 2.5% 25% 50% 75% 97.5%
Sigma 0.1627 0.0067 0.1500 0.1581 0.1626 0.1671 0.1762
JSigma 1.1700 0.0785 1.0350 1.1140 1.1650 1.2190 1.3440
mu 0.0499 0.0073 0.0354 0.0449 0.0498 0.0549 0.0640
Jmu 0.1773 0.0958 -0.0080 0.1123 0.1738 0.2392 0.3794
lamda 0.1990 0.0191 0.1630 0.1855 0.1989 0.2119 0.2375
Xi[1] 0.1654 1.1781 -2.1130 -0.6071 0.1267 0.9430 2.5780
Xi[2] 0.1736 1.1661 -2.1350 -0.5642 0.1355 0.9508 2.4491
Xi[3] 0.1747 1.1714 -2.1201 -0.6144 0.1444 0.9444 2.5400
.....
.....
J[804] 1.0000 0.0000 1.0000 1.0000 1.0000 1.0000 1.0000
J[805] 1.0000 0.0000 1.0000 1.0000 1.0000 1.0000 1.0000
J[806] 1.0000 0.0000 1.0000 1.0000 1.0000 1.0000 1.0000
deviance -788.9082 63.0674 -912.0050 -831.9250 -790.0000 -746.4000 -664.6875
DIC info (using the rule, pD = var(deviance)/2)
pD = 1988.7 and DIC = 1199.8
DIC is an estimate of expected predictive error (lower deviance is better).