[R] mixed model random interaction term log likelihood ratio test

seatales ssphadke at uh.edu
Fri Apr 15 03:57:44 CEST 2011

1. The three levels of the vector DrugPair actually represent three
genotypes, which are some randomly chosen genotypes from a population of
many genotypes. That's why I thought it was justified as random effect. 
Does estimating them as random make sense then? 
2. Also could you please elaborate on your suggestion "=ran"?
3. Wouldn't (MatingPair|DrugPair) represent nesting rather than the
interaction as a random effect? I got (1|DrugPair:MatingPair) from the
following post:

> I am using the following model
> model1=lmer(PairFrequency~MatingPair+(1|DrugPair)+(1|DrugPair:MatingPair),
> data=MateChoice, REML=F)
> 1. After reading around through the R help, I have learned that the above
> code is the right way to analyze a mixed model with the MatingPair as the
> fixed effect, DrugPair as the random effect and the interaction between
> these two as the random effect as well. Please confirm if that seems
> correct.

  You should probably send this sort of question to the 
r-sig-mixed-models mailing list ...

  You probably want (MatingPair|DrugPair) rather than
Whether REML=FALSE or REML=TRUE depends what you want
to do next.

> 2. Assuming the above code is correct, I have model2 in which I remove the
> interaction term, model3 in which I remove the DrugPair term and model4 in
> which I only keep the fixed effect of MatingPair.

> 5. I could not find how to input the random interaction term while using
> lme? Is it the following way? Would someone please guide me to some
> already
> existing posts or help here?

  = ran
> lme(PairFrequency~MatingPair,
> random=~(1|DrugPair)+(1|DrugPair:MatingPair),
> data=MateChoice, method="ML")...is this the right way? would lme give me
> loglikelihood ratio test values (L.ratio)?

  See above.

> Sujal P.
> p.s: If it matters how data is arranged, then I have one vector called
> MatingPair which has 3 levels and another vector DrugPair which also has 3
> levels. The PairFrequency data is a count data and is normally
> distributed.
> The data are huge, hence I am not able to post it here.

  It is probably unwise to estimate DrugPair as a random effect if
it only has three levels.

> View this message in context:
> Sent from the R help mailing list archive at Nabble.com.
> 	[[alternative HTML version deleted]]

R-help at r-project.org mailing list
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

View this message in context: http://r.789695.n4.nabble.com/mixed-model-random-interaction-term-log-likelihood-ratio-test-tp3448718p3451092.html
Sent from the R help mailing list archive at Nabble.com.

More information about the R-help mailing list