Skip to contents

Model Multivariate Distribution by Vine Copula

model_vine.Rd

Estimate the multivariate distribution of the model data via vine copula estimation (see rvinecopulib::vine).

Usage

model_vine(data, margins_controls, ...)

Arguments

data

data.frame Data to estimate the multivariate distribution.

margins_controls

list A list with arguments to be passed to kde1d::kde1d(). Currently, there can be

  • mult numeric vector of length one or d; all bandwidths for marginal kernel density estimation are multiplied with mult. Defaults to log(1 + d) where d is the number of climate variables.

  • xmin numeric vector of length d; see kde1d::kde1d().

  • xmax numeric vector of length d; see kde1d::kde1d().

  • bw numeric vector of length d; see kde1d::kde1d().

  • deg numeric vector of length one or d; kde1d::kde1d().

  • type character vector of length one or d; must be one of c, cont, continuous for continuous variables, one of d, disc, discrete for discrete integer variables, or one of zi, zinfl, zero-inflated for zero-inflated variables.

...

Arguments are passed to rvinecopulib::vinecop to specify the structure of vines and margins. Note that the ellipsis of observed and model data are specified with the same arguments.

Value

The PIT-transformed margins from estimate_margins(). Additionally the data frame contains the attribute vine with the vine copula model and the attribute kde with the kernel density estimation of the data.