bread.maxLik {maxLik} | R Documentation |
Extracting an estimator for the ‘bread’ of the sandwich estimator,
see bread
.
## S3 method for class 'maxLik' bread( x, ... )
x |
an object of class |
... |
further arguments (currently ignored). |
Matrix, the inverse of the expectation of the second derivative (Hessian matrix) of the log-likelihood function with respect to the parameters, usually equal to the variance covariance matrix of the parameters times the number of observations.
The sandwich package must be loaded before this method can be used.
This method works only if maxLik
was called
with argument grad
equal to a gradient function or
(if no gradient function is specified)
argument logLik
equal to a log-likelihood function
that return the gradients or log-likelihood values, respectively,
for each observation.
Arne Henningsen
## ML estimation of exponential duration model: t <- rexp(100, 2) loglik <- function(theta) log(theta) - theta*t ## Estimate with numeric gradient and hessian a <- maxLik(loglik, start=1 ) # Extract the "bread" library( sandwich ) bread( a ) all.equal( bread( a ), vcov( a ) * nObs( a ) )