cormat.mbcsec: Working Correlation Matrices for Multivariate Box-Cox...

In rdmatheus/mbcsec: Multivariate Box-Cox Symmetric Distributions Generated From Elliptical Copula

Description

Current available correlation matrices in the mbcsec package.

Usage

ind()

un(d)

arma(p = 0, q = 0)

cluster(
  id,
  type = c("independence", "ar1", "ma1", "exchangeable", "unstructured")
)

matern(D, smt = 0.5)

Arguments

d	Dimension of the correlation matrix.
p, q	Order of the autoregressive and the moving average component, respectively, passed as arguments to arma().
id	Subject id for longitudinal/clustered data. This is a vector of the same lenght of the number of observations. Please note that data must be sorted in way that observations from the same cluster are contiguous.
type	A character string specifying the correlation structure among groups for longitudinal/clustered data. At the moment, the following are implemented: independence Working independence. ar1 Autoregressive of order 1. ma1 Moving average of order 1. exchangeable1 Exchangeable. unstructured Unstructured
D	Matrix with values of the distances between pairs of data locations for spatial data.
smt	Value of the shape parameter of the Matern correlation class. The default smt = 0.5 corresponds to an exponential correlation model.

Details

The functions related to the association structures are a direct adaptation of the functions of the gcmr package. The documentation of the original functions of the package can be seen at cormat.gcmr documentation. The available correlation matrices are:

Function	Correlation
ind	Working independence.
un	Unstructured
arma	ARMA(p, q)
cluster	Longitudinal/clustered data
matern	Matern spatial correlation

Each type of structure will require different arguments for the association matrix P to be completed. However, all functions return a list of the following components:

• npar: Number of parameters associated with the correlation structure.

• start: A function function(y) that returns the initial value for use in optimization algorithms. Its argument is the vector/matrix of observations y.

• P: A function function(alpha, d) which returns the association matrix itself. Its arguments are the parameter vector associated with the correlation matrix structure and the dimension of the correlation matrix.

• name: Name of the specified correlation structure.

Author(s)

Rodrigo M. R. Medeiros <[e-mail]>

References

Guido Masarotto, & Cristiano Varin (2017). Gaussian Copula Regression in R. Journal of Statistical Software, 77(8), 1–26.

rdmatheus/mbcsec documentation built on April 27, 2021, 1:50 p.m.