emtp2: Performs Gaussian likelihood optimization under Laplacian...

In sebastian-engelke/graphicalExtremes: Statistical Methodology for Graphical Extreme Value Models

Performs Gaussian likelihood optimization under Laplacian matrix constraints.

Description

This function implements a block descent algorithm to find the maximum of the Gaussian log-likelihood under the constraint that the concentration matrix is a Laplacian matrix. See \insertCiteroe2021;textualgraphicalExtremes for details.

Usage

emtp2(Gamma, tol = 1e-06, verbose = TRUE, initial_point = TRUE)

Arguments

Gamma	conditionally negative semidefinite matrix. This will be typically the empirical variogram matrix.
tol	The convergence tolerance. The algorithm terminates when the sum of absolute differences between two iterations is below tol.
verbose	if TRUE (default) the output will be printed.
initial_point	if TRUE (default), the algorithm will construct an initial point before the iteration steps.

Value

A list consisting of:

G_emtp2	The optimal value of the variogram matrix
it	The number of iterations

References

\insertAllCited

See Also

Other parameter estimation methods: data2mpareto(), emp_chi(), emp_chi_multdim(), emp_vario(), fmpareto_HR_MLE(), fmpareto_graph_HR(), loglik_HR()

sebastian-engelke/graphicalExtremes documentation built on Jan. 10, 2025, 10:02 a.m.