Hello,
I estimated three paramters using non informative prior(all paramters following
uniform distribution)
the output is:
Error in optim(pars, li_func, control = list(fnscale = -1), hessian = TRUE, :
non-finite finite-difference value [1]
How can I solve it using uniform distribution
ople keep coming along
> and sticking things into it."
> -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )
>
>
> On Thu, Dec 10, 2015 at 9:26 AM, hms Dreams <cute_loo...@hotmail.com> wrote:
> > Hello,
> > I estimated three para
Hi,
I estimate 3 paramters using MOM and Bayesian methods
How can I estimate the reliability(R) and hazard(h) functions??
Is it correct if I estimated R and h like MLE by substitute the estimators and
put any value for x in the formula of R and h??
I need help please
thank you
noor
Any suggestions :( ??From: cute_loo...@hotmail.com
To: r-help@r-project.org
Subject: Metro_Hastings I wrote my code again
Date: Sun, 15 Feb 2015 21:47:25 +0300
Hi again :)
I wrote my code here:
library(MHadaptive)
baysianlog=function (param,data)
{ alpha=param[1]
Hi,
I'm trying to use method of moments estimation to estimate 3 unkown paramters
delta,k and alpha.
so I had system of 3 non linear equations:
1) [delta^(1/alpha) *gamma (k-(1/alpha)) ]/gamma(k) = xbar
2) [delta^(2/alpha) *gamma (k-(2/alpha)) ]/gamma(k) = 1/n *sum (x^2)
3) [delta^(3/alpha)
Hi again :)
I wrote my code here:
library(MHadaptive)baysianlog=function (param,data)
{ alpha=param[1]
gam=param[2]
delta=param[3]
x=data
n =length(x)
Hi :)anybody can help me please I'm trying to use Metro_Hastings (
MHadaptive package)the proplem is: How can I know the covariance matrix(
prop_sigma ) to enter it in Metro_Hastings:
mcmc_r=Metro_Hastings(li_func=baysianlog, pars=c(1,1,1), prop_sigma
Hi again :)
my code is in the attachment file
the problem I think in the :
mcmc_r=Metro_Hastings(li_func=baysianlog,
pars=c(1,1,1),par_names=c('alpha','gamma','delta'),data=x
)
because I did not write the prop_sigma because I don't know how can I
calcalute the covariance matrix.
somebody
8 matches
Mail list logo