[R] Obtaining SE from the hessian matrix

Thomas Lumley tlumley at u.washington.edu
Thu Feb 19 18:22:09 CET 2004

On Thu, 19 Feb 2004, Timur Elzhov wrote:
> So, what is the _right_ way for obtatining SE? Why two those formulas above
> differ?

If you are maximising a likelihood then the covariance matrix of the
estimates is (asymptotically) the inverse of the negative of the Hessian.

The standard errors are the square roots of the diagonal elements of the

So if you have the Hessian you need to invert it, if you have the
covariance matrix, you don't.


More information about the R-help mailing list