mobirep (version 0.2.3)

JT.KDE.ap: Fits the bivariate joint tail model with Kernel density estimator

Description

Fits the bivariate joint tail model with Kernel density estimator (Adapted from Cooley et al. (2019))and provides estimates of a conditional or joint exceedance level curve with a probability corresponding to 'pobj'. Also provides estimates of dependence measures.

Usage

JT.KDE.ap(
  u2,
  pbas,
  pobj,
  beta,
  vtau,
  devplot = F,
  kk,
  mar1,
  mar2,
  px,
  py,
  interh = NA
)

Arguments

u2

Two column data frame

pbas

joint return period to be modelled with a kde

pobj

objective joint return period modelled with the joint tail model

beta

smoothing parameter for the transition between asymptotic dependent and independent regimes near the axes

vtau

estimate of the rank correlation between the two variables

devplot

additional plots for development (significantly slows the function)

kk

uniform margins of the original data

mar1

Values of the first margin

mar2

Values of the second margin

px

Uniform values of the first margin with a mixed distribution (empirical below and gpd above a threshold)

py

Uniform values of the second margin with a mixed distribution (empirical below and gpd above a threshold)

interh

type of hazard interrelation 'comb' for compound and 'casc' for cascade,

Value

a list containing the following:

• levelcurve - data frame the objective containing level curve with a return level 'pobj'

• wq0ri - matrix of the base level curve with a return level 'pbas'

• etaJT - threshold dependent extremal dependence measure

• chiJT - threshold dependent coefficient of tail dependence

References

Tilloy, A., Malamud, B.D., Winter, H. and Joly-Laugel, A., 2020. Evaluating the efficacy of bivariate extreme modelling approaches for multi-hazard scenarios. Natural Hazards and Earth System Sciences, 20(8), pp.2091-2117.

Cooley, D., Thibaud, E., Castillo, F. and Wehner, M.F., 2019. A nonparametric method for producing isolines of bivariate exceedance probabilities. Extremes, 22(3), pp.373-390.

See Also

chi

Examples

# NOT RUN {
# Inport data
data(porto)
tr1=0.9
tr2=0.9
fire01meantemp=na.omit(fire01meantemp)
u=fire01meantemp

# Compute uniform margins
marg=Margins.mod(tr1,tr2,u=fire01meantemp)
kk=marg$uvar
pp=marg$uvar_ext
uu=marg$val_ext
upobj=0.001
vtau=cor.test(x=u[,1],y=u[,2],method="kendall")$estimate
interh="comb"
# }
# NOT RUN {
# Fit JT-KDE model
jtres<-JT.KDE.ap(u2=u,pbas=0.01,pobj=upobj,beta=100,kk=kk,vtau=vtau,
devplot=FALSE,mar1=uu[,1],mar2=uu[,2],px=pp[,1],py=pp[,2],interh=interh)
plot(jtres$levelcurve)
# }