nacTiming: Timing for Sampling Frailties of Nested Archimedean Copulas

In copula: Multivariate Dependence with Copulas

Timing for Sampling Frailties of Nested Archimedean Copulas

Description

This function provides measurements of user run times for the frailty variables involved in a nested Archimedean copula.

Usage

nacFrail.time(n, family, taus, digits = 3, verbose = FALSE)

Arguments

n	integer specifying the sample size to be used for the random variates V_0 and V_{01}.
family	the Archimedean family (class "acopula") for which V_0 and V_{01} are sampled.
taus	numeric vector of Kendall's taus. This vector is converted to a vector of copula parameters \theta, which then serve as \theta_0 and \theta_1 for a three-dimensional fully nested Archimedean copula of the specified family. First, for each \theta_0, n random variates V_0 are generated. Then, given the particular \theta_0 and the realizations V_0, n random variates V_{01} are generated for each \theta_1 fulfilling the sufficient nesting condition; see paraConstr in acopula.
digits	number of digits for the output.
verbose	logical indicating if nacFrail.time output should generated while the random variates are generated (defaults to FALSE).

Value

A k \times k matrix of user run time measurements in milliseconds (1000*system.time(.)[1]) where k is length(taus). The first column contains the run times for generating the V_0s. For the submatrix that remains if the first column is removed, row i (for {\theta_0}_i) contains the run times for the V_{01}s for a particular \theta_0 and all the admissible \theta_1s.

See Also

The class acopula and our predefined "acopula" family objects in acopula-families. For some timings on a standard notebook, see demo(timings) (or the file ‘timings.R’ in the demo folder).

Examples

## takes about 7 seconds:% so we rather test a much smaller set in R CMD check

nacFrail.time(10000, "Gumbel", taus=  c(0.05,(1:9)/10, 0.95))

system.time(
print( nacFrail.time(1000,  "Gumbel", taus = c(0.5,1,6,9)/10) )
)

copula documentation built on Feb. 7, 2024, 3:01 p.m.