[R] Externally studentized residuals for Generalized Least Squares model (gls, package: nlme)

[Wilfried Maps]

Having estimated a generalized least squares model using gls (non-diagonal covariance matrix, one structural parameter estimated from the data), I wonder whether there is an efficient way to compute jackknifed/externally studentized residuals. The residuals.gls method does not offer this possibility; neither have I found any mention of the hat-matrix in the documentation.

Kind regards,
Wilfried Maps,
Zurich
Switzerland

____________________________________________________________
FREE 3D MARINE AQUARIUM SCREENSAVER - Watch dolphins, sharks & orcas on your desktop!