Returns the observed information matrix from a fitted nlreg
model.
# S3 method for nlreg
obsInfo(object, par, mu, v, m1 = NULL, m2 = NULL, v1 = NULL,
v2 = NULL, …)a fitted nlreg object such as returned by a call to
nlreg.
a vector of parameter values where each element is named after the
parameter it represents. If missing, the values in the
ws$allPar component of object are used.
numerical vector containing the mean function evaluated at each
data point. If missing, the fitted values saved in
object are used.
numerical vector containing the variance function evaluated at
each data point. If missing, the values of the weights
component of object are used.
a matrix whose rows represent the gradients of the mean function
evaluated at each data point. If NULL, the gradient
attribute of the object returned by a call to
Dmean is used.
a three-way array whose rows represent the Hessian of the mean
function evaluated at each data point. If NULL, the
hessian attribute of the object returned by a call to
Dmean is used.
a matrix whose rows represent the gradient of the variance
function evaluated at each data point. If NULL, the
gradient attribute of the object returned by a call to
Dvar is used.
a three-way array whose rows represent the Hessian of the variance
function evaluated at each data point. If NULL, the
hessian attribute of the object returned by a call to
Dvar is used.
absorbs any additional argument.
the observed information matrix of the fitted nonlinear model passed
through the object argument.
This function is a method for the generic function
obsInfo for objects inheriting from class
nlreg.