corFDG: Sample pairwise dependence coefficients
In FDGcopulas: Multivariate Dependence with FDG Copulas

Description Usage Arguments Details Value Author(s) References See Also Examples

Computes sample (i.e., empirical) pairwise dependence coefficients such as the Kendall's tau, the Spearman's rho, and the upper tail dependence coefficient (the later being proved to have good statistical properties only for extreme-value copulas and in the case of known margins).

1	corFDG(x, depcoefType)

`x`	the data
`depcoefType`	type of dependence coefficient: one of 'kendall', 'spearman', or 'utdc'

The function 'corFDG' simply calls 'cor()' when 'depcoefType' is either 'kendall' or 'spearman'. If it is 'utdc', then the sample upper tail dependence coefficient for extreme-value copulas introduced in the reference below is computed.

A matrix of size 'd' times 'd' where 'd' is the number of variables. The element in the i-th row and j-th column is the dependence coefficient between the i-th and j-th variable.

Gildas Mazo

Ferreira, M., Nonparametric estimation of the tail-dependence coefficient, REVSTAT–Statistical Journal, 2013

cor

## Generate an extreme-value copula
myFDGcopula <- FDGcopula("frechet", c(.3,.5,.7,.9), extremevalue=TRUE)
dat <- rFDG(100, myFDGcopula)
## Compute the sample upper tail dependence coefficient given in the reference
corFDG(dat, "utdc")