subrank-package {subrank}

Computes Copula using Ranks and Subsampling

Description

Estimation of copula using ranks and subsampling. The main feature of this method is that simulation studies show a low sensitivity to dimension, on realistic cases.

Details

The DESCRIPTION file:

Package:	subrank
Type:	Package
Title:	Computes Copula using Ranks and Subsampling
Version:	0.9.9.3
Date:	2023-04-06
Author:	Jerome Collet
Maintainer:	Jerome Collet <[e-mail]>
Description:	Estimation of copula using ranks and subsampling. The main feature of this method is that simulation studies show a low sensitivity to dimension, on realistic cases.
License:	GPL (>= 3)
LazyLoad:	yes
NeedsCompilation:	yes

Index of help topics:

corc                    Function to estimate copula using ranks and
                        sub-sampling
corc0                   Function to estimate copula using ranks and
                        sub-sampling, minimal version.
desscop                 Discrete copula graph, a two-dimensional
                        projection
desscoptous             Discrete copula graph, ALL two-dimensional
                        projections
estimdep                Dependence estimation
predictdep              Probability forecasting
predonfly               Probability forecasting
simany                  Test statistic distribution under any
                        hypothesis
simnul                  Test statistic distribution under independence
                        hypothesis
subrank-package         Computes Copula using Ranks and Subsampling

Taking a sample, its dimension, and a sub-sample size, allows to estimate a discretized copula. This object has interesting features: convergence to copula, robustness with respect to dimension.

Author(s)

Jerome Collet

Maintainer: Jerome Collet <[e-mail]>

Examples

lon <- 31
a <- 2.85
x <- rnorm(lon)
y = a*x^2+rnorm(lon)
tablo = as.data.frame(cbind(x,y))
c=corc(tablo,c(1,2),8)
desscop(c,1,2)