0
$\begingroup$

I have been trying to estimate the basic stochastic volatility model using OpenBUGS via R and at an stage of the following command. Please can you comment for the command that can give me the estimated parameter values of the model?

library(tsbugs)
y <- svpdx$pdx

# create and write bugs script
sv0 <- sv.bugs(y)
writeLines(sv0$bug, "sv0.txt")

# estimate model parameters in R2OpenBUGS
library(R2OpenBUGS)
sv0.bug <- bugs(data=sv0$data, 
                inits=list(inits(sv0)),
                param=c(nodes(sv0, "prior")$name, "h"),
                model="sv0.txt",
                n.iter=11000, n.burnin=10000, n.chains=1)
$\endgroup$
  • $\begingroup$ For the SV model estimation I have been trying to model by using OpenBUGS via R and at an stage of the following command!y y<- svpdx$pdx sv0 <- sv.bugs(y, sim=TRUE) print(sv0) $\endgroup$ – user25287 May 9 '13 at 6:35
  • $\begingroup$ > sv0.bug <- bugs(data = sv0$data, inits = list(init), param = c(nodes(sv0, "prior")$name,"y.sim","h"), model = "sv0.txt", n.iter = 11000, n.burnin = 1000, n.chains = 1) How can I estimate the parameter values of a basic SV model? a command that could print an estimated value for the parameters (alpha0, alpha1, sigma) or (beta, mu, sigma) of a SV model $\endgroup$ – user25287 May 9 '13 at 6:48
  • $\begingroup$ This question appears to be off-topic because it is about how to use R, & too old to migrate. $\endgroup$ – gung - Reinstate Monica May 21 '14 at 16:16
1
$\begingroup$

Tell the bugs command which parameters you want to monitor param=c("psi0", "psi1", "tau")....

sv0.bug<-bugs(data=sv0$data, 
              inits=list(inits(sv0)),
              param=c("psi0", "psi1", "tau"),
              model="sv0.txt",
              n.iter=11000, n.burnin=10000, n.chains=1)

Then use print.bugs command to give the summary statistics of the MCMC estimation...

> print(sv0.bug)
Inference for Bugs model at "sv0.txt", 
Current: 1 chains, each with 11000 iterations (first 10000 discarded)
Cumulative: n.sims = 1000 iterations saved
           mean   sd   2.5%    25%    50%    75%  97.5%
psi0       -0.9  0.2   -1.2   -1.0   -0.9   -0.7   -0.5
psi1        1.0  0.0    1.0    1.0    1.0    1.0    1.0
tau         0.2  0.0    0.1    0.2    0.2    0.2    0.2
deviance 1753.7 12.6 1729.0 1745.0 1753.0 1763.0 1776.0

DIC info (using the rule, pD = Dbar-Dhat)
pD = 36.6 and DIC = 1790.0
DIC is an estimate of expected predictive error (lower deviance is better).
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.