[R] [R-sig-ME] Calculating F values for lme function

peter dalgaard pd@|gd @end|ng |rom gm@||@com
Tue Jan 15 19:41:25 CET 2019


Or at least don't do it with lme() because it basically gets them wrong (I believe even its author agrees). The situation is rather better with lme4 and the pbkrtest package, although one should always be wary of low denominator DF cases because, even at the best of times, results rely heavily on assumptions of normal distribution.

-pd

> On 15 Jan 2019, at 18:42 , Bert Gunter <bgunter.4567 using gmail.com> wrote:
> 
> Ricardo:
> You may do better posting on the r-sig-mixed-models list, which is
> specifically devoted to such topics.
> 
> FWIW, re calculating F-values for mixed effects models, I think many say:
> don't.
> 
> Bert Gunter
> 
> "The trouble with having an open mind is that people keep coming along and
> sticking things into it."
> -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )
> 
> 
> On Tue, Jan 15, 2019 at 8:36 AM Jeff Newmiller <jdnewmil using dcn.davis.ca.us>
> wrote:
> 
>> You should use Reply-All to make sure the discussion continues to include
>> the mailing list.
>> 
>> Have you looked at the help for lme?
>> 
>> lme is non-trivial, so it may take some reading. I only have a few of the
>> references listed in the help file, and none with me at the moment.
>> 
>> On January 15, 2019 7:36:22 AM PST, RICARDO ALVARADO BARRANTES <
>> RICARDO.ALVARADO using ucr.ac.cr> wrote:
>>> Thanks for your response, however my understandig of all this
>>> programming is very limited. Is there any source where I can read about
>>> F calculation for those models?
>>> 
>>> Thanks for your time
>>> 
>>> Ricardo
>>> 
>>> El 14-01-2019 16:47, Jeff Newmiller escribió:
>>> 
>>>> Fortunately, nlme is open source [1 [1]][2 [2]], so you can follow
>>> along in as much detail as you like.
>>>> 
>>>> Note that capitalization matters in R... NLME is not correct.
>>>> 
>>>> [1]  https://github.com/cran/nlme/blob/master/R/lme.R
>>>> [2] https://cran.r-project.org/package=nlme
>>>> 
>>>> On January 14, 2019 1:59:29 PM PST, RICARDO ALVARADO BARRANTES
>>> <RICARDO.ALVARADO using ucr.ac.cr> wrote:
>>>> 
>>>>> I have a question related to the funcion LME in the library NLME.  I
>>>>> would like to understand how the F values are calculated, since the
>>>>> output only shows the degrees of freedom but doen't show the sums of
>>>>> squares involved in those calculations.
>>>>> 
>>>>> Thanks for your attention.
>>>>> 
>>>>> Ricardo
>>>>> 
>>>>> [[alternative HTML version deleted]]
>>>>> 
>>>>> _______________________________________________
>>>>> R-sig-mixed-models using r-project.org mailing list
>>>>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>>> 
>>> 
>>> 
>>> Links:
>>> ------
>>> [1] https://github.com/cran/nlme/blob/master/R/lme.R
>>> [2] https://cran.r-project.org/package=nlme
>> 
>> --
>> Sent from my phone. Please excuse my brevity.
>> 
>> ______________________________________________
>> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

-- 
Peter Dalgaard, Professor,
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Office: A 4.23
Email: pd.mes using cbs.dk  Priv: PDalgd using gmail.com



More information about the R-help mailing list