[R] Test for autocorrelation in nlme model

[Revilla,AJ (pgt)]

Dear all,

I am fitting a nonlinear mixed-effects model from a balanced panel of data using nlme. I would like to know whay would be the best options for formally testing for autocorrelation. Is it possible to carry out a Durbin-Watson test on a nlme object? As far as I've seen, I think the durbin.watson function from the car package just works on lm objects.

Thank you very much,

Antonio