bivquant (version 0.1)

geomqu2d_norm2: On Affine Equivariant Multivariate Quantiles

Description

This function fits empirical bivariate quantiles as proposed by Chakraborty, B. (2001). 2 dimensional data and with p=2

Usage

geomqu2d_norm2(data, probs, alpha, k = 8)

Arguments

data

must be a (n,2) matrix of observations.

probs

vector of probs which is used to calculate the us

alpha

missing or a vector of length 3 with distict values form 1 to n

k

number of us per prob

References

Chakraborty, B. (2001). On affine equivariant multivariate quantiles. Annals of the Institute of Statistical Mathematics, 53, 380--403.

See Also

geomqu for details.

Examples

# NOT RUN {
require("MASS")
require("mvtnorm")
set.seed(42)
n <- 50
mu <- c(6, 10)
#correlated responses
rho <- 0.5
Sigma <- matrix(c(
    1.0, rho,
    rho, 1.0
  ),
  ncol=2, byrow=TRUE)

X <- rmvnorm(n, mu, Sigma)
result <- geomqu2d_norm2(X, probs=c(0.8,0.9), k=8)
plot(result)

#now independent responses
rho <- 0.0
Sigma <- matrix(c(
    1.0, rho,
    rho, 1.0
  ),
  ncol=2, byrow=TRUE)

X <- rmvnorm(n, mu, Sigma)
result <- geomqu2d_norm2(X, probs=c(0.8,0.9), k=8)
plot(result)

#now some non-normal data
X <- dgp_cop(n, family="clayton", margins=c("norm", "norm"),
		 paramMargins=list(list(mean = 4, sd = 1), list(mean = 4, sd = 5)),
		 rho=1.75)
result <- geomqu2d_norm2(X, probs=c(0.8,0.9), k=8)
plot(result)

# }