R help - Mar 2008 - lme library

Dear authors,
I?m an Italian PhD student and I?m dealing with linear mixed models.

I?d like to use your lme library, but I have a problem.

I?m able to estimate a null model.
For example, using SAS data, I can estimate the model:
lme(y ~ 1, data = Mississippi, random = ~ 1|influent, method="ML")

As suggested in the literature I want to ?test? the significance of the
second level variance. So, I would like also to estimate a linear model
without random effects. Is it possible with your library?
In the description of the function lme I found that the random part is
optional, but I don't know how to remove it.

I tried also other R functions (as glm, lme, etc), but I don?t find any
function that implements the models with the method ?ML?.

Can you help me, please?

Really thanks for you help,
Bests
Roberta Varriale


Ps I prefer your new look!

<roberta_varriale <at> ds.unifi.it> writes:
> I?m able to estimate a null model.
> For example, using SAS data, I can estimate the model:
> lme(y ~ 1, data = Mississippi, random = ~ 1|influent,
method="ML")
> 
> As suggested in the literature I want to ?test? the significance of the
> second level variance. So, I would like also to estimate a linear model
> without random effects. Is it possible with your library?
> In the description of the function lme I found that the random part is
> optional, but I don't know how to remove it.

  In general, linear models without random effects are fit with
lm() , which is part of base R.  If you need other fancy things
(heteroscedasticity, spatial autocorrelation etc.) you can use
gls in the nlme package.

  Ben Bolker