[R-sig-ME] NLME model syntax
nrm2010 at zoho.com
Fri Feb 25 18:51:46 CET 2011
Yes, I did try that and I had the same problem.
I also tried it without the "list", as in "fixed = list...", based on
previous bug reports, and that doesn't run either.
But if I linearize it and use lme instead of nlme, it runs perfectly.
Also, since I failed to mention this in the original message,
it's nlme v. 3.1-98, R v. 2.11.1 with TINN-R interface on Windows OS.
---- On Fri, 25 Feb 2011 02:29:37 -0700 Thierry ONKELINX wrote ----
>Have you tried to use a regular data.frame instead of a groupedData object?
>ir. Thierry Onkelinx
>Instituut voor natuur- en bosonderzoek
>team Biometrie & Kwaliteitszorg
>Research Institute for Nature and Forest
>team Biometrics & Quality Assurance
>tel. + 32 54/436 185
>Thierry.Onkelinx at inbo.be
>To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of.
>~ Sir Ronald Aylmer Fisher
>The plural of anecdote is not data.
>~ Roger Brinner
>The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data.
>~ John Tukey
>> -----Oorspronkelijk bericht-----
>> Van: r-sig-mixed-models-bounces at r-project.org
>> [mailto:r-sig-mixed-models-bounces at r-project.org] Namens nrm2010
>> Verzonden: donderdag 24 februari 2011 23:16
>> Aan: r-sig-mixed-models at r-project.org
>> Onderwerp: [R-sig-ME] NLME model syntax
>> I'm trying to use NLME for a non-linear model with one random
>> effect that is the same as the one grouping level (chamber).
>> Using the following
>> test <- nlme(flux ~ b0 * exp((b1*soiltemp) - (b2*soiltemp^2))
>> * vpd^b3 * mstsoil2^b4 * airtemp^b5, data = ac5, fixed =
>> list(b0 + b1 + b2 + b3 + b4 + b5 ~ 1), random = chamber ~ 1,
>> start = c(b0 = 570, b1 = 0.08, b2 = 0.002,
>> b3 = -0.06, b4 = 3, b5 = 0.3), subset = airtemp > 0)
>> I always get the error message
>> "Error in eval(expr, envir, enclos) : object 'chamber' not found"
>> Data "ac5" is a groupedData object with chamber as the
>> grouping factor:
>> > head(ac5)
>> Grouped Data: flux ~ soiltemp + vpd + mstsoil2 + airtemp | chamber
>> I've tried many variations such as
>> random = list(chamber ~ 1) or random = ~1|chamber
>> or adding the "groups" statement or trying to put chamber on the
>> RHS of the model statement, after the fixed effects,
>> but I always get the same error message.
>> What is the correct way to formulate the call to nlme? Or is
>> this not a syntax error?
>> Thank you in advance.
>> Toby Gass
>> tobygass at cnr dot colostate dot edu
>> R-sig-mixed-models at r-project.org mailing list
More information about the R-sig-mixed-models