Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 4 down vote favorite
1

I am examining the difference between a physical feature of different species of animals. Due to the nature of my experiments I'm using a nonlinear mixed model with the following setup:

lme(log10(feature) ~ log10(Body.mass) + factor(Trial.Number), random = ~1 | IndividualID, data=animals, subset=Frfactor=="low", na.action=na.omit )

where subset=Frfactor=="low" refers to a specific speed range that I'm interested in.

I get great results which I'm happy about. But now I want to see how species affects my feature. Since the same conditions apply (tons of repeated effects) I've kept the lme and changed the structure to: 

lme(log10(feature) ~ specfactor + factor(Trial.Number), random = ~1 | IndividualID, data=animals, subset=Frfactor=="low", na.action=na.omit )

where specfactor lists the names of the species. Looking at the p values it looks like these species are not significantly different from the intercept (which is specfactorserval). However when I create a boxplot, it certainly looks like there are some big interspecies differences!

I guess because the lme is a test for regressions, it doesn't really make sense to use when comparing the feature against categorical variables. But I still need to account for repeated effects. My question is if there's a better way to test for significance between species using the boxplot? I need the usual- p-values, confidence intervals. The "list" command seems to fall short of such comparisons. I don't know if a t-test would cut it.

Thanks!

PS I originally posted an image of my test results and of the boxplot, but I'm too new of a user to be allowed....

share|improve this question
Do your boxplots take into account the fact that your repeated measures are within individuals? If so, they are probably pretty useless for letting you guess about the outcome of the mixed model. – John Mar 23 '11 at 23:12
Is this structure the correct way to account for individual repeated measures? bwplot(specfactor ~ log10(feature), random=~1|IndividualID, subset=Frfactor=="low", data=animals) It doesn't generate an error but it also doesn't change my boxplot results. – user3761 Mar 24 '11 at 14:44
If you're using lme from the nlme package, isn't that a linear mixed method rather than nonlinear? The nonlinear version is nlme. See cran.r-project.org/web/packages/nlme/nlme.pdf – Michelle Jan 21 '12 at 23:54
Perhaps you could post the code that created the boxplot, as the problem is as likely to be with that as with your models – Peter Ellis Jan 24 '12 at 11:06

1 Answer

up vote 1 down vote

Your model (I think) is using the same slopes for all species, and perhaps this is why the boxplots look different.

If the feature shows an allometric reln with the body mass, then there are various possible models about that relationship varies with species and individuals within a species. Species in different groups (eg Reptiles vs mammals vs birds) might share a relationship (= slope) but they could also be in different size ranges.

I think you should add body mass to the second model and test for interaction terms between species and bodywt.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.