[R-sig-ME] mixed effect model query

ONKELINX, Thierry Thierry.ONKELINX at inbo.be
Thu Aug 6 10:19:24 CEST 2009


Dear Grant,

You have not enough levels to use random effects. You have only 2 and 4
levels whereas you need at least 6 to get a decent variance estimate. So
I would suggest to use the tubs as fixed effects. Hence your model
simplifies to a logistic regression.

HTH,

Thierry


------------------------------------------------------------------------
----
ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature
and Forest
Cel biometrie, methodologie en kwaliteitszorg / Section biometrics,
methodology and quality assurance
Gaverstraat 4
9500 Geraardsbergen
Belgium
tel. + 32 54/436 185
Thierry.Onkelinx at inbo.be
www.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 Mcdonald, Grant
Verzonden: woensdag 5 augustus 2009 15:36
Aan: r-sig-mixed-models at r-project.org
Onderwerp: [R-sig-ME] mixed effect model query

Dear sir/Madam,

I have a designed experiment where females insects were either allocted
an old or young male insect and allowed 30 minutes in which to mate.

My response is there for a 1(success) or 0(failure to mate), and my
explanotory variables are therefore, age of male, the ratio between male
and female size, and index of male and female  activity level, and the
time it took within the 30monute mating trial to start a mating attempt
in the first place.

I also have though information on which mass rearing tubs the insects
were grown,   two tubs for females and two tubs for young males and two
tubs for old males (the tubs for female and youg males are the same).  I
wanted to add these in as random effects.  All combinations between tubs
were represented almost equally in a 2x4 experimental design (2 female
tubs and 4 male tubs)


my model would look like this, 


model1<-lmer(successful~maleage*relweight*malemobtrue*femmobtrue*timetoa
ttemptsecs+(1|maletub/femtub),family=binomial)

does this seem correct as i feel i cant used aov due to the non normal
error structure and glm will not allow me to use tub as a random effect



Kind  Regards
Grant McDonald
Imperial college London

P.S. I apologise if this message is in poor format as I have not emailed
before and i am unsure as to how to go about it.

_______________________________________________
R-sig-mixed-models at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

Dit bericht en eventuele bijlagen geven enkel de visie van de schrijver weer 
en binden het INBO onder geen enkel beding, zolang dit bericht niet bevestigd is
door een geldig ondertekend document. The views expressed in  this message 
and any annex are purely those of the writer and may not be regarded as stating 
an official position of INBO, as long as the message is not confirmed by a duly 
signed document.




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