vcov.feglm computes an estimate of the covariance matrix of the estimator of the
structural parameters from objects returned by feglm. The estimate is obtained
using the Hessian, the scores, or a combination of boths after convergence.
# S3 method for feglm
vcov(object, type = c("hessian", "outer.product",
"sandwich", "clustered"), cluster = NULL, cluster.vars = NULL, ...)an object of class "feglm".
the type of covariance estimate required. "hessian" refers to the inverse
of the negative expected Hessian after convergence and is the default option.
"outer.product" is the outer-product-of-the-gradient estimator,
"sandwich" is the sandwich estimator (sometimes also refered as robust estimator),
and "clustered" computes a clustered covariance matrix given some cluster variables.
a symbolic description indicating the clustering of observations.
deprecated; use cluster instead.
other arguments.
The function vcov.feglm returns a named matrix of covariance estimates.
Multi-way clustering is done using the algorithm of Cameron, Gelbach, and Miller (2011). An example is provided in the vignette "Replicating an Empirical Example of International Trade".
Cameron, C., J. Gelbach, and D. Miller (2011). "Robust Inference With Multiway Clustering". Journal of Business & Economic Statistics 29(2).