[R-sig-ME] More naive questions: Speed comparisons? what is a "stack imbalance" in lmer? does lmer center variables?
Douglas Bates
bates at stat.wisc.edu
Wed Sep 23 20:08:43 CEST 2009
On Wed, Sep 23, 2009 at 12:37 PM, Douglas Bates <bates at stat.wisc.edu> wrote:
> On Wed, Sep 23, 2009 at 12:21 PM, Ben Bolker <bolker at ufl.edu> wrote:
>> Source *is* available:
>
> Thanks for the correction, Ben. I withdraw my comments about ADMB and
> welcome it to the Open Source software arena.
I have also exchanged email off-list with Kevin Wright and would like
to clarify that I was not labeling Kevin as dishonest in my response
and I sincerely regret my poor phrasing if I left that impression.
I am not quite Stallmanesque in my approach to open-source software
(for example, I will use the phrase "open-source") but I am somewhat
of a purist. I do essentially all of my computing on Linux systems,
by choice. I know of the thousands of hours of work, probably
hundreds of thousands by now, done by members of R-Core and many, many
others to make R what it is today. I also know of the importance of
licenses on open-source software. In a very real sense the licenses
are what makes the whole open-source software movement work. They may
not be important to casual useRs but they should be important to
developeRs.
This is why it pains me when software that is not open source is said
to be available through R because an interface has been written.
First it is unlikely that I would even be able to use it. Most of the
time the binary is a Windows binary and not of use to me. Secondly,
if I am going to devote many hours of my time to producing software
and make it all freely available, including the sources, I don't want
others to say that their wonderful software has similar status when
they can see what I do but I can't see what they do.
It turns out that I was wrong when I characterized ADMB as
proprietary. It was proprietary but it is now open source and I think
that is great. I offer my apologies if I have offended anyone with my
inaccurate and poorly considered statements.
>> Peter Dalgaard wrote:
>>> Ben Bolker wrote:
>>>> As of sometime last year (? I think ?), ADMB is
>>>> free/gratis/libre/open source (BSD licensed).
>>>
>>> As of _next_ year is more like it. Their downloads are still
>>> binary-only. BSD does not imply Open Source when you don't have the
>>> sources, and "open source project" in this case means a project to make
>>> the software open source. The intention appears to be honourable, though.
>>>
>>> Even before that,
>>>> glmmADMB (which was an R package with a binary component, available for
>>>> download) was "free as in beer". In its current status, I think of ADMB
>>>> in the same category as WinBUGS -- a powerful, albeit sometimes
>>>> unwieldy, tool that can be used through an R interface to solve general
>>>> problems by writing model descriptions in a non-R language.
>>>> I have to agree with Kevin that the diversity of mixed model software
>>>> tools is a good thing.
>>>>
>>>> cheers
>>>> Ben Bolker
>>>>
>>>> Douglas Bates wrote:
>>>>> Got to disagree with you, Kevin. admb and asreml are not part of R,
>>>>> even in the general sense of R packages. R is Open Source - they are
>>>>> not. Tacking on an R interface to proprietary software and saying it
>>>>> is available in R is misleading and dishonest.
>>>>>
>>>>> On Wed, Sep 23, 2009 at 8:54 AM, Kevin Wright <kw.stat at gmail.com> wrote:
>>>>>> Paul,
>>>>>>
>>>>>> It appears to me that the published timings you reference are
>>>>>> comparing the __nlme__ package with other software. So the answer is
>>>>>> yes, nlme really is that slow for some models. You are probably aware
>>>>>> that the __lme4__ package has faster algorithms.
>>>>>>
>>>>>> There are many ways to fit mixed models in R including nlme, lme4,
>>>>>> MCMCglmm, admb asreml, BUGS, etc. If I was teaching a course, I would
>>>>>> try to expose students to at least two of those in some detail and
>>>>>> touch briefly on the others: nlme can fit a variety of complex
>>>>>> varaiance structures, lme4 has faster algorithms, asreml is the only
>>>>>> choice of animal/plant breeders and has commercial support, MCMCglmm
>>>>>> has some Bayesian aspects and can fit some heteroskedastic variance
>>>>>> structures, admb is used in Fish & Wildlife, etc.
>>>>>>
>>>>>> Mixed model fitting in R is definitely not a case of "one size fits all".
>>>>>>
>>>>>> Kevin Wright
>>>>>>
>>>>>>
>>>>>> On Wed, Sep 23, 2009 at 1:36 AM, Paul Johnson <pauljohn32 at gmail.com> wrote:
>>>>>>> Sent this to r-sig-debian by mistake the first time. Depressing.
>>>>>>>
>>>>>>> 1. One general question for general discussion:
>>>>>>>
>>>>>>> Is HLM6 faster than lmer? If so, why?
>>>>>>>
>>>>>>> I'm always advocating R to students, but some faculty members are
>>>>>>> skeptical. A colleague compared the commercial HLM6 software to lmer.
>>>>>>> HLM6 seems to fit the model in 1 second, but lmer takes 60 seconds.
>>>>>>>
>>>>>>> If you have HLM6 (I don't), can you tell me if you see similar differences?
>>>>>>>
>>>>>>> My first thought was that LM6 uses PQL by default, and it would be
>>>>>>> faster. However, in the output, HLM6 says:
>>>>>>>
>>>>>>> Method of estimation: restricted maximum likelihood
>>>>>>>
>>>>>>> But that doesn't tell me what quadrature approach they use, does it?
>>>>>>>
>>>>>>> Another explanation for the difference in time might be the way HLM6
>>>>>>> saves the results of some matrix calculations and re-uses them behind
>>>>>>> the scenes. If every call to lmer is re-calculating some big matrix
>>>>>>> results, I suppose that could explain it.
>>>>>>>
>>>>>>> There are comparisons from 2006 here
>>>>>>>
>>>>>>> http://www.cmm.bristol.ac.uk/learning-training/multilevel-m-software/tables.shtml
>>>>>>>
>>>>>>> that indicate that lme was much slower than HLM, but that doesn't help
>>>>>>> me understand *why* there is a difference.
>>>>>>>
>>>>>>> 2. What does "stack imbalance in .Call" mean in lmer?
>>>>>>>
>>>>>>> Here's why I ask. Searching for comparisons of lmer and HLM, I went
>>>>>>> to CRAN & I checked this document:
>>>>>>>
>>>>>>> http://cran.r-project.org/web/packages/mlmRev/vignettes/MlmSoftRev.pdf
>>>>>>>
>>>>>>> I *think* these things are automatically generated. The version
>>>>>>> that's up there at this moment (mlmRev edition 0.99875-1) has pages
>>>>>>> full of the error message:
>>>>>>>
>>>>>>> stack imbalance in .Call,
>>>>>>>
>>>>>>> Were those always there? I don't think so. What do they mean?
>>>>>>>
>>>>>>> 3. In the HLM6 output, there is a message at the end of the variable list:
>>>>>>>
>>>>>>> '%' - This level-1 predictor has been centered around its grand mean.
>>>>>>> '$' - This level-2 predictor has been centered around its grand mean.
>>>>>>>
>>>>>>> What effect does that have on the estimates? I believe it should have
>>>>>>> no effect on the fixed effect slope estimates, but it seems to me the
>>>>>>> estimates of the variances of random parameters would be
>>>>>>> changed. In order to make the estimates from lmer as directly
>>>>>>> comparable as possible, should I manually center all of the variables
>>>>>>> before fitting the model? I'm a little stumped on how to center a
>>>>>>> multi-category factor before feeding it to lmer. Know what I mean?
>>>>>>>
>>>>>>> pj
>>>>>>>
>>>>>>> --
>>>>>>> Paul E. Johnson
>>>>>>> Professor, Political Science
>>>>>>> 1541 Lilac Lane, Room 504
>>>>>>> University of Kansas
>>>>>>>
>>>>>>> _______________________________________________
>>>>>>> R-sig-mixed-models at r-project.org mailing list
>>>>>>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>>>>>>>
>>>>>> _______________________________________________
>>>>>> R-sig-mixed-models at r-project.org mailing list
>>>>>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>>>>>>
>>>>> _______________________________________________
>>>>> R-sig-mixed-models at r-project.org mailing list
>>>>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>>>>
>>>
>>>
>>
>>
>> --
>> Ben Bolker
>> Associate professor, Biology Dep't, Univ. of Florida
>> bolker at ufl.edu / www.zoology.ufl.edu/bolker
>> GPG key: www.zoology.ufl.edu/bolker/benbolker-publickey.asc
>>
>> _______________________________________________
>> 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