[R] LINEAR MIXED EFFECT

[ANARPCG]

Douglas Bates-2 wrote:
> 
> On Thu, Nov 12, 2009 at 10:14 AM, milton ruser <milton.ruser at gmail.com>
> wrote:
>> Hi Ana,
>>
>> I am not quite sure if it is the problem, but if you call your data.frame
>> as
>> exp,
>> you will crash exp() function... try use another name for your
>> data.frame.
>>
>> By the way, I suggest you not use attach().
>>
>> Try something like model<-lme(weight~date*diet, data=yourdataframe)
>>
>> good luck
> 
> and include the random specification in the call to lme, not as a
> separate assignment.
> 
>> milton
>>
>> On Thu, Nov 12, 2009 at 5:43 AM, ANARPCG <a.gouveia07 at imperial.ac.uk>
>> wrote:
>>
>>>
>>>
>>>
>>>
>>> Milton's point is dead-on, and I would highly encourage you to give the
>>> posting guide a look.
>>>
>>> That said... you might try "na.action = na.omit" in your call to...
>>> actually, we don't know what function you are using (see first point).
>>> Regardless, sounds like you have missing data and na.action is set to
>>> na.fail (ie, "fail" if any missing data).
>>>
>>> cheers, Dave
>>>
>>>
>>> milton ruser wrote:
>>> >
>>> > Dear Ana Golveia,
>>> >
>>> > It is completelly impossible someone realise what kind or help you
>>> need
>>> or
>>> > what is happening. I suggest you give a look on the posting guide,
>>> mainly
>>> > that part about a minimum reproducible code with self explaining
>>> > information, etc.
>>> >
>>> > Cheers
>>> >
>>> > milton
>>> >
>>> > On Wed, Nov 11, 2009 at 7:22 AM, ANARPCG <a.gouveia07 at imperial.ac.uk>
>>> > wrote:
>>> >
>>> >>
>>> >> CAN ANYONE PLEASE HELP ME WITH THIS
>>> >> i HAVE TO DO A MIXED EFFECT LINEAR MODEL WITH MY DATA DUE TO THE FACT
>>> >> THAT
>>> >> I
>>> >> have pseudoreplication!
>>> >> Although after reading and trying it for several times can get around
>>> due
>>> >> to
>>> >> "Error in na.fail.default(list(date = c(1L, 2L, 3L, 4L, 5L, 6L, 7L,
>>> 8L,
>>> >> :
>>> >> missing values in object"
>>> >> I uploaded my data file
>>> >> Thank you so much
>>> >> Kind regards
>>> >> AG
>>> >> http://old.nabble.com/file/p26300394/rawoctobercalciumexperiment2.txt
>>> >> rawoctobercalciumexperiment2.txt
>>> >>
>>> >> --
>>> >> View this message in context:
>>> >> http://old.nabble.com/LINEAR-MIXED-EFFECT-tp26300394p26300394.html
>>> >> Sent from the R help mailing list archive at Nabble.com.
>>> >>
>>> >> ______________________________________________
>>> >> R-help at r-project.org mailing list
>>> >> https://stat.ethz.ch/mailman/listinfo/r-help
>>> >> PLEASE do read the posting guide
>>> >>
>>> http://www.R-project.org/posting-guide.html<http://www.r-project.org/posting-guide.html>
>>> <http://www.r-project.org/posting-guide.html>
>>> >> and provide commented, minimal, self-contained, reproducible code.
>>> >>
>>> >
>>> >       [[alternative HTML version deleted]]
>>> >
>>> > ______________________________________________
>>> > R-help at r-project.org mailing list
>>> > https://stat.ethz.ch/mailman/listinfo/r-help
>>> > PLEASE do read the posting guide
>>> >
>>> http://www.R-project.org/posting-guide.html<http://www.r-project.org/posting-guide.html>
>>> > and provide commented, minimal, self-contained, reproducible code.
>>> >
>>> > sorry I am new on this things
>>> > the point is after trying to run the model all that happens is:
>>> >> exp<-read.table(file=file.choose(),header=T)
>>> >> attach(exp)
>>> >> names(exp)
>>> > [1] "group"     "date"      "diet"      "weight"    "thickness"
>>> "length"
>>> > [7] "width"     "liplength" "lipwidth"
>>> >>
>>> exp$diet=factor(exp$diet,levels=c("zeropercent","tenpercent","twentypercent","thirtypercent","fortypercent","cuttleprecent"))
>>> >> exp=na.omit(exp)
>>> >> library(nlme)
>>> >> random=~date
>>> >> model<-lme(weight~date*diet)
>>> > Error in na.fail.default(list(date = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L,
>>>  :
>>> >   missing values in object
>>> >
>>> >  I have pseudoreplications due to the fact that the measurements of
>>> the
>>> > replicates have different starting points so I was advised to do lme.
>>> I
>>> > never used it before and I cant get arround with it! the help I wanted
>>> > from you is to help me to understand how to do a "runable" model!
>>> >
>>> >
>>> >
>>> http://old.nabble.com/file/p26315302/rawoctobercalciumexperiment2.txt
>>> rawoctobercalciumexperiment2.txt
>>> --
>>> View this message in context:
>>> http://old.nabble.com/LINEAR-MIXED-EFFECT-tp26300394p26315302.html
>>>  Sent from the R help mailing list archive at Nabble.com.
>>>
>>> ______________________________________________
>>> R-help at r-project.org mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>> PLEASE do read the posting guide
>>> http://www.R-project.org/posting-guide.html<http://www.r-project.org/posting-guide.html>
>>> and provide commented, minimal, self-contained, reproducible code.
>>>
>>
>>        [[alternative HTML version deleted]]
>>
>> ______________________________________________
>> R-help at r-project.org mailing list
>> 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.
>>
> 
> ______________________________________________
> R-help at r-project.org mailing list
> 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.
> 
> 
:handshake:it did work finally thk for the help
it went like this
data<-read.table("H:\\5.11.09\\rawoctobercalciumexperiment2.txt",header=T)
names(data)
data<-na.omit(data)
library(nlme)
model5<-lme(lipwidth~date*diet,random=~1|date|diet,data=data)
summary(model5)
plot.lme(model5)

-- 
View this message in context: http://old.nabble.com/LINEAR-MIXED-EFFECT-tp26300394p26336616.html
Sent from the R help mailing list archive at Nabble.com.