cnqr_sel: Select Vines using CNQR

In vincenzocoia/cmc: Copula-Marginal Composition Method

Description

Select from vine models using CNQR. The vines can only differ in the last columns of their copula and copula parameter matrices, and are assumed to have the response in the upper-right corner of each vine array. The vine whose forecasts score optimally is selected.

Usage

cnqr_sel(rv_list, sc, y, uind, QY = identity)

Arguments

rv_list	list of 'rvine' objects, each of which may only differ in the last columns of the copula and copula parameter matrices.
sc	Scoring rule to use for the regression, as in the output of scorer.
y	Vector of response data.
uind	Matrix of independent uniform predictors, as in the output of pcondseq, of the predictors in the last column of the (common) vine array. If we call "b" that column without the first (response) variable, the input matrix should be the PIT scores of variables b[1]; b[2]|b[1]; b[3]|b[1:2]; etc.
QY	Quantile function of the response y, which accepts a vector of values (quantile levels) in (0,1). It should return quantiles, either in the form of a vector corresponding to the input, or in the form of a matrix with columns corresponding to the inputted quantile levels and rows corresponding to the observations of y (thus allowing for each value in y to come from different distributions).

Value

Outputs the "best" entry of rv_list.

Note

This function assumes that the inputted vines may only differ in the last column of the copula and copula parameter matrices, and does not check to see that this is the case.

See Also

cnqr_est for CNQR when the model space is a parameter space.

vincenzocoia/cmc documentation built on Nov. 18, 2019, 12:04 a.m.