Findalphabeta_beta: Quantile difference when tuning Beta distribution...

In shazhe/mvst0: Multi-variate ST modelling on globe

Description

This function returns the normalised difference between specified and required 95 percentiles of the Beta distribution. This function can then be passed to an optimisation routine to find required parameter values.

Usage

Findalphabeta_beta(pars, p95)

Arguments

pars	the two shape parameters of the Beta distribution
p95	the desired 95 percentile

Value

A numeric which is a measure of the discrepancy between the desired and real 95 percentile.

Examples

require(actuar)
initpars <- c(2,6)
hyp  = optim(par=c(2,6),Findalphabeta_beta, p95=0.12)
hyp_shape1 <- hyp$par[1]
hyp_shape2 <- hyp$par[2]
# Now simulate from a Beta with these parameters and verify quantiles
X <- rbeta(shape1 = hyp_shape1, shape2 = hyp_shape2,n=10000)
print(quantile(X,0.95))

shazhe/mvst0 documentation built on May 29, 2019, 9:20 p.m.