[R-sig-ME] profile() for lmer

Douglas Bates bates at stat.wisc.edu
Thu Apr 15 20:04:53 CEST 2010


On Thu, Apr 15, 2010 at 5:40 AM, pierre nouvellet
<pierrenouvellet at hotmail.com> wrote:

> Thanks again to Rob!

> the call to 'profile(fm1ML at env)'  worked perfectly!
> it is really nice to see it working smoothly!!

Thanks to those who picked up on this.  Both Martin and I have been
doing a lot of development on lme4a in the past couple of weeks,
including fundamental changes to the internal representation.  We
didn't mean to turn the process of determining the profiles into a
treasure hunt - that just sort-of happened.

I should post a warning that the profile is likely to break again in
the near future when I move in the wonderful new and improved class
representation currently lurking around as a resurrected lmer2
function.  We will get the profiling working again after we break it
but there is a lot going on under the hood right now and some breakage
is inevitable.

As others have discovered, lme4a now depends on the Rcpp package and,
inadvertently, on an unreleased version.  That should be fixed soon.

Thanks for your patience.


> pierre
>
>> Date: Thu, 15 Apr 2010 22:07:30 +1200
>> From: p.taylor at niwa.co.nz
>> To: pierrenouvellet at hotmail.com; r-sig-mixed-models at r-project.org
>> Subject: Re: [R-sig-ME] profile() for lmer
>>
>> Hi Pierre,
>>
>> I'm having the same problem. I discovered a suggestion on another mailing list (stat.ethz.ch/mailman/listinfo/r-help) that using a delta argument would work ie pr1ML<-profile(fm1ML,delta=0.2). However, I have tried that and several smaller steps, but to no avail.
>>
>> I too am using lme4a and R-2.10.1 on windows 2007 professional.
>>
>> Any help from anyone would be greatly appreciated.
>>
>> Paul Taylor
>> Pelagic Fisheries Scientist
>> NIWA
>> New Zealand.
>>
>> >>> pierre nouvellet 04/15/10 4:29 AM >>>
>>
>> Hi,Hi,
>>
>> >From the draft book on lme4:
>> using lme4a, and the dyestuff data, I call profile and get:
>>
>> > profile(fm1ML)
>>
>> Error in UseMethod("profile") :
>>
>> no applicable method for 'profile' applied to an object of class
>> "lmer"
>>
>>
>> any suggestions?
>> using a R-2.10.1 on windows vista
>>
>> pierre
>>
>>
>> _________________________________________________________________
>> Hotmail: Free, trusted and rich email service.
>>
>> [[alternative HTML version deleted]]
>>
>> _______________________________________________
>> R-sig-mixed-models at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>> NIWA is the trading name of the National Institute of Water & Atmospheric Research Ltd.
>
> _________________________________________________________________
> Hotmail: Powerful Free email with security by Microsoft.
>
>        [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>




More information about the R-sig-mixed-models mailing list