FactorCopulaModel (version 0.1.1)

zetaDep: Empirical version of zeta(alpha) tail-weighted dependence measure

Description

Empirical version of zeta(alpha) tail-weighted dependence measure

Usage

zetaDep(dat,alpha,rank=TRUE,lowertail=FALSE)

Value

Dependence measure zeta(alpha)

Arguments

dat

nx2 data matrix with values (in (0,1) if rank=FALSE)

alpha

vector of alpha>0 for zeta measure

rank

TRUE (default) if to convert data matrix to uniform scores in (0,1)

lowertail

TRUE if lower tail-weighted dependence measure, default is FALSE

Details

This is a central dependence measure if alpha =1 and upper tail-weighted is alpha>>1

References

Lee D, Joe H, Krupskii P (2018). J Nonparametric Statistics, 30(2), 262-290

Examples

data(euro07gf)
udat = euro07gf$uscore
euro07names = colnames(udat)
d = ncol(udat)
for(j2 in 2:d)
{ for(j1 in 1:(j2-1))
  { zetaU = zetaDep(udat[,c(j1,j2)],alpha=15,rank=FALSE,lowertail=FALSE)
    zetaL = zetaDep(udat[,c(j1,j2)],alpha=15,rank=FALSE,lowertail=TRUE)
    zeta1 = zetaDep(udat[,c(j1,j2)],alpha=1,rank=FALSE,lowertail=FALSE)
    cat(j1,j2,round(zeta1,3),round(zetaL,3),round(zetaU,3),euro07names[j1],euro07names[j2],"\n")
  }
}