pacotestRvineSeq {pacotest} | R Documentation |
Sequentially Testing the Simplifying Assumption for R-Vine Copulas
Description
The function can be used to test the simplifying assumption for R-vine copulas in a sequential manner. Each pair-copula from the second tree on is tested to be a (j-1)-th order partial copula. To apply the function one needs to provide the data and a specified/estimated R-vine copula model in form of a RVineMatrix from the VineCopula-package. Additionally, a pacotest options list, which can be generated with the pacotestset
function, needs to be provided.
Usage
pacotestRvineSeq(data, RVM, pacotestOptions,
level = 0.05, illustration = 2, stopIfRejected = TRUE)
Arguments
data |
A (n x d) matrix (or data frame) of [0,1] data (i.e. uniform margins). |
RVM |
An RVineMatrix object (VineCopula-package) which includes the structure, the pair-copula families and parameters of an R-vine copula. |
pacotestOptions |
A options list generated by the |
level |
The level of the test. |
illustration |
Either 1 or 2. If illustration = 1, the p-value for each test for a (j-1)-th order partial copula is displayed. If illustration = 2, a progress information is displayed for each tree. It consists of the individual test level and the number of H0 rejections. |
stopIfRejected |
A logical variable indicating whether the sequential test procedure should be stopped in the first tree where an H0 for one of the conditional copulas is rejected. |
Value
A list consisting of the following elements:
pacotestResultLists |
A matrix in the same structure like the |
pValues |
A matrix in the same structure like the |
testResultSummary |
A data.frame summarizing the test results.
The first column, |
Author(s)
Malte S. Kurz
References
Kurz, M. S. and F. Spanhel (2022), "Testing the simplifying assumption in high-dimensional vine copulas", Electronic Journal of Statistics 16 (2), pp. 5226-5276.
Spanhel, F. and M. S. Kurz (2019), "Simplified vine copula models: Approximations based on the simplifying assumption", Electronic Journal of Statistics 13 (1), pp. 1254-1291.
See Also
pacotest-package
, pacotest
, pacotestset
, pacotestRvineSingleCopula
Examples
# Sample data and R-vine copula selection are taken
# from the documentation of RVineStructureSelect
# of the VineCopula package.
# Obtain sample data
data(daxreturns, package ="VineCopula")
dataSet = daxreturns[1:750,1:4]
# Specify an R-vine copula model
# (can be obtained by calling: RVM = VineCopula::RVineStructureSelect(dataSet))
vineStructure = matrix(c(3,4,1,2,0,2,4,1,0,0,1,4,0,0,0,4),4,4)
families = matrix(c(0,5,2,2,0,0,2,14,0,0,0,14,0,0,0,0),4,4)
par = matrix(c(0,0.8230664,0.1933472,0.6275062,
0,0,0.2350109,1.6619945,
0,0,0,1.599363,
0,0,0,0),4,4)
par2 = matrix(c(0,0,11.757700,4.547847,
0,0,17.15717,0,
0,0,0,0,0,0,0,0),4,4)
RVM = VineCopula::RVineMatrix(vineStructure, families, par, par2)
# Specify a pacotestOptions list:
pacotestOptions = pacotestset('CCC')
# Test for the simplifying assumption.
pacotestResultList = pacotestRvineSeq(dataSet, RVM,
pacotestOptions)