CoSMoS (version 2.1.2)

actpnts: AutoCorrelation Transformed Points

Description

Transforms a Gaussian process in order to match a target marginal lowers its autocorrelation values. The actpnts evaluates the corresponding autocorrelations for the given target marginal for a set of Gaussian correlations, i.e., it returns (\(\rho_x , \rho_z\)) points where \(\rho_x\) and \(\rho_z\) represent, respectively, the autocorrelations of the target and Gaussian process.

Usage

actpnts(margdist, margarg, p0 = 0, distbounds = c(-Inf, Inf))

Arguments

margdist

target marginal distribution

margarg

list of marginal distribution arguments

p0

probability zero

distbounds

distribution bounds (default set to c(-Inf, Inf))

Examples

library(CoSMoS)

## here we target to a process that has the Pareto type II
## marginal distribution with scale parameter 1 and shape parameter 0.3
## (note that all parameters have to be named)
dist <- 'paretoII'
distarg <- list(scale = 1, shape = .3)

x <- actpnts(margdist = dist, margarg = distarg, p0 = 0)
x

## you can see the points by using
ggplot(x,
       aes(x = rhox,
           y = rhoz)) +
  geom_point(colour = 'royalblue4', size = 2.5) +
  geom_abline(lty = 5) +
  labs(x = bquote(Autocorrelation ~ rho[x]),
       y = bquote(Gaussian ~ rho[z])) +
  scale_x_continuous(limits = c(0, 1)) +
  scale_y_continuous(limits = c(0, 1)) +
  theme_classic()