README.md
In ExtremalDep: Extremal Dependence Models

`ExtremalDep`: Extremal Dependence Models

A set of procedures for parametric and non-parametric modelling of the dependence structure of multivariate extreme-values is provided. The statistical inference is performed with non-parametric estimators, likelihood-based estimators and Bayesian techniques. It adapts the methodologies of Beranger and Padoan (2015) , Marcon et al. (2016) , Marcon et al. (2017) , Marcon et al. (2017) and Beranger et al. (2021) . This package also allows for the modelling of spatial extremes using flexible max-stable processes. It provides simulation algorithms and fitting procedures relying on the Stephenson-Tawn likelihood as per Beranger at al. (2021) .

Version 0.0.4-2 updates:

Fixes a typo in dExtDep() for in the Asymetric Logistic model;
Replaces the Calloc() and Free() calls in the .C files by the R_* prefixed counterparts since STRICT_R_HEADERS=1 becomes the default with R 4.5.0;
Improves some entries in the manual.

Version 0.0.4-3 updates:

Inclusion of the PAMfmado() function written by Philippe Naveau.

Version 0.0.4-4 updates:

Fixes resetting graphical parameters in plot_ExtDep.np() when type = "Qsets";
Replaces closeAllConnections() by stopCluster() in fExtDepSpat().

Version 0.0.4-5 updates:

Improvement to dExtDep() function when model="HR" and "ET";
New lambda.hr() function that can be used to define the parameters of the trivariate Husler-Reiss model. Given two parameters, a range for the third parameter is provided to ensure positive definite matrices in the exponent function;
Improve efficiency when manipulating matrices:
- t(A) %*% B is replaced by crossprod(A,B) (and vice versa);
- solve(A) is replaced by chol2inv(chol(A));
- t(x) %*% solve(A) %*% x is replaced by sum(forwardsolve(t(chol(A)),x));
Define outputs of fExtDep(), fExtDep.np() and fExtDepSpat() to be of class ExtDep_Freq, ExtDep_Bayes, ExtDep_npFreq, ExtDep_npBayes, ExtDep_npEmp and ExtDep_Spat;
Make use of class methods for plot() and summary() functions replacing the previous plot.ExtDep(), etc;
New est(), StdErr(), logLik(), bic(), tic() to extract outputs from objects of class ExtDep_Freq, ExtDep_Bayes and ExtDep_Spat.