pdNatural-class {Matrix} | R Documentation |
A class of general, positive-definite symmetric matrices parameterized by the logarithm of the diagonal elements and Fisher's z transformation of the correlations.
Objects can be created by calls of the form new("pdNatural",
...)
or by the generic constructor function pdNatural
.
Frequently the constructor is given a formula only, creating an
uninitialized pdNatural
object which is later assigned a
value.
pdNatural
objects are primarily used to represent the
variance-covariance matrix or the precision matrix of random-effects
terms in mixed-effects models.
param
:"numeric", from class
"pdMat"
, a parameter vector of length
[q(q+1)]/2 where q is the number of
rows (and columns) in the positive-definite matrix.form
:"formula", from class
"pdMat"
, a formula for the objectNames
:"character", from class
"pdMat"
, names for the rows (and columns) of the
positive-definite matrix.
Class "pdMat"
, directly.
signature(x = "pdNatural", nlev = "numeric",
value = "matrix")
: update the pdNatural
object in the EM
algorithm for a mixed-effects model.signature(x = "pdNatural", A = "matrix",
nlev = "numeric")
: evaluate the gradient of the log-likelihood
in a linear mixed-effects model.signature(object = "pdNatural")
: extract the
parameter.signature(object = "pdNatural", value =
"numeric")
: assign the parameter.signature(from = "pdNatural", to = "pdmatrix")
:
extract the positive-definite matrix represented by the object.signature(from = "pdNatural", to = "pdfactor")
:
extract a square-root factor of the matrix represented by the
object. This factor has a logDet
attribute giving the
logarithm of its determinant. In the case of pdNatural
these are both scalars and the logDet
attribute is the
logarithm of the absolute value of the factor.signature(x = "pdNatural")
: the dimensions of the
positive-definite matrix represented by the object.signature(object = "pdNatural")
: a
logical scalar indicating if the object is initialized. signature(object = "pdNatural", covariate =
"missing")
: the logarithm of the determinant of the factor of
the positive-definite matrix represented by the object.signature(x = "pdNatural")
: the gradient of
the positive definite matrix with respect to the parameter vector.signature(a = "pdNatural", b = "missing")
: a
pdNatural
object representing the inverse of the
positive-definite matrix represented by this object.signature(object = "pdNatural")
: summarize the
object.