lme questions (was [R] difference between splus and R)

Faheem Mitha faheem at email.unc.edu
Fri Apr 7 16:39:49 CEST 2000

On Fri, 7 Apr 2000, Prof Brian Ripley wrote:

> I *have* looked at the documentation.  It does not give a reference for
> the validity of REML-based LRTs, so can you please supply one?

Sorry, I can't. Perhaps someone else can?

> There is a warning note:
>      Likelihood comparisons are not meaningful for objects fit using
>      restricted maximum likelihood and with different fixed effects.
> which does not say that the converse *is* meaningful. nlme2 even gives the
> comparisons in the excluded case. Bill Venables' warning (V&R3 p.203) is
> rather stronger.

> S does not usually stop you doing non-meaningful statistics, so do not
> assume that because it gives a result it is `legitimate'.

Point taken. However, nothing I have read suggests the converse *isn't*
meaningful, and this does appear to be the default behaviour of anova.lme.
If there is a problem with this, it should say so up front. I would be
grateful if someone (perhaps the authors of nlme) could clarify this one
way or the other.

r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list