Dear Community,
I am trying to write (update) a code for the following problem.
Lets assume we have a beta distribution.
I know one quantile, lets say, 10% of the mass lies above .8, that is
between .8 and 1.
In addition, I know that the average of this "truncated tail" is a
given number, lets say .86.
I have found the beta.select function in the LearnBayes package, which
is as follows:
function (quantile1, quantile2)
{
betaprior1 = function(K, x, p) {
m.lo = 0
m.hi = 1
flag = 0
while (flag == 0) {
m0 = (m.lo + m.hi)/2
p0 = pbeta(x, K * m0, K * (1 - m0))
if (p0 < p)
m.hi = m0
else m.lo = m0
if (abs(p0 - p) < 1e-04)
flag = 1
}
return(m0)
}
p1 = quantile1$p
x1 = quantile1$x
p2 = quantile2$p
x2 = quantile2$x
logK = seq(-3, 8, length = 100)
K = exp(logK)
m = sapply(K, betaprior1, x1, p1)
prob2 = pbeta(x2, K * m, K * (1 - m))
ind = ((prob2 > 0) & (prob2 < 1))
app = approx(prob2[ind], logK[ind], p2)
K0 = exp(app$y)
m0 = betaprior1(K0, x1, p1)
return(round(K0 * c(m0, (1 - m0)), 2))
}
I assume one could change this code to get the results I need, but some
parts of the function are not clear for me, any help would be greatly
appreciated.
Thanks a lot:
Daniel
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
