R help - Nov 2011 - lme4:glmer with nested data

Dear all,

I have the following dataset with results from an experiment with individual
bats that performed two tasks related to prey capture under different
conditions:

X variables:
indiv - 5 individual bats used in the experiment; all of which performed both
tasks
task - 2 tasks that each individual bat had to perform
dist - 5 repeated measures of individual bats at 5 different distances from the
object

all x variables I treat as categorical factors with levels

Y - I have 8 dependent variables related to the structure of ultrasound calls
emitted by bats when performing each task. I know I can use them together in the
same model with the function ?cbind()? but each variable behaves a bit
differently. Thus, I guess it would be better to build 8 separate models.

I believe "indiv" should be a random effect in the model;
"dist" and "task" should be fixed effects.

I?d like to use the ?glmer? (lme4) function to test two hypotheses:

Main hypothesis:
There are differences in Y measurements between tasks, which are related also to
distance from the object.

Secondary hypothesis:
Differences in Y measurements between tasks do not depend on the individual.


I guess the simplest model for an AIC model selection would be:
print(Model.01<-glmer(y~task*dist+(1|indiv))
 - so any model that provides more details should have a lower (better)  AIC
score.
I?m not sure if I?m coding the model correctly, so my hypothesis would be
properly tested.

1- Literature suggests to get rid of the pseudo-replication: my repeated
measures (?dist?) seem to behave like longitudinal data (as it is basically a
time series). This way, "indiv" would be nested in "dist".
Furthermore, "dist" levels have different variance, so it would be
good to group the data and somehow tell the model, that it should ignore
differences in variance.
(1|dist:indiv) or (dist|indiv)?
I am still wondering if the ?weights=? argument would apply here?

2- ?dist? is nested in ?task?, as for both tasks I have the same distances
measured.
According to the description of the package ?lme4?, I should write:
print(Model.02<-glmer(y~task*dist+(1|indiv)+(1|task:dist))

3- according to the text -book ?The R book? I understand that I should do the
following (as mentioned for the ratliver treatment-dataset):
rename factor levels to unique labels:
taskdist<-task:dist
taskdistindiv<-task:dist:indiv
print(Model.03<-glmer(y~task+(1|taskdist)+(1|taskdistindiv)))

Or, pooling 1 and 3 together myself I would end up with:
print(Model.04<-glmer(y~dist*task+(1|indiv)+(1|task:dist)+(1|dist:indiv))

I doubt that all of them actually describe correctly what I want the model to
answer...

I did not find any directly related comment in the R help.

Thank you for your attention and for any help you may provide.

--

1. Post this on the R-sig-mixed-models list, not here.

2. (The following "advice" should be treated cautiously): Forget it!
With
only 5 bats, you have too little information to estimate variance
components. Treat the bats as fixed effects and fit via lm (or glm if some
of your responses are not gaussian).

As your statistical skills seem a mite weak, I would also suggest that you
collaborate with your local statistician. As I would not submit my brain
(diminished as it may be)  to someone whose training comes largely from
reading "Brain surgery for Dummies,"  neither would I trust the data
analysis of someone whose statistical background is analogously informed.

Apologies if I have misjudged.

Cheers,
Bert

On Mon, Nov 14, 2011 at 5:44 AM, <hijita@gmx.net> wrote:
> Dear all,
>
> I have the following dataset with results from an experiment with
> individual bats that performed two tasks related to prey capture under
> different conditions:
>
> X variables:
> indiv - 5 individual bats used in the experiment; all of which performed
> both tasks
> task - 2 tasks that each individual bat had to perform
> dist - 5 repeated measures of individual bats at 5 different distances
> from the object
>
> all x variables I treat as categorical factors with levels
>
> Y - I have 8 dependent variables related to the structure of ultrasound
> calls emitted by bats when performing each task. I know I can use them
> together in the same model with the function “cbind()” but each variable
> behaves a bit differently. Thus, I guess it would be better to build 8
> separate models.
>
> I believe "indiv" should be a random effect in the model;
"dist" and
> "task" should be fixed effects.
>
> I´d like to use the “glmer” (lme4) function to test two hypotheses:
>
> Main hypothesis:
> There are differences in Y measurements between tasks, which are related
> also to distance from the object.
>
> Secondary hypothesis:
> Differences in Y measurements between tasks do not depend on the
> individual.
>
>
> I guess the simplest model for an AIC model selection would be:
> print(Model.01<-glmer(y~task*dist+(1|indiv))
>  - so any model that provides more details should have a lower (better)
>  AIC score.
> I’m not sure if I’m coding the model correctly, so my hypothesis would be
> properly tested.
>
> 1- Literature suggests to get rid of the pseudo-replication: my repeated
> measures (“dist”) seem to behave like longitudinal data (as it is basically
> a time series). This way, "indiv" would be nested in
"dist". Furthermore,
> "dist" levels have different variance, so it would be good to
group the
> data and somehow tell the model, that it should ignore differences in
> variance.
> (1|dist:indiv) or (dist|indiv)?
> I am still wondering if the “weights=” argument would apply here?
>
> 2- “dist” is nested in “task”, as for both tasks I have the same distances
> measured.
> According to the description of the package “lme4”, I should write:
> print(Model.02<-glmer(y~task*dist+(1|indiv)+(1|task:dist))
>
> 3- according to the text -book “The R book” I understand that I should do
> the following (as mentioned for the ratliver treatment-dataset):
> rename factor levels to unique labels:
> taskdist<-task:dist
> taskdistindiv<-task:dist:indiv
> print(Model.03<-glmer(y~task+(1|taskdist)+(1|taskdistindiv)))
>
> Or, pooling 1 and 3 together myself I would end up with:
>
print(Model.04<-glmer(y~dist*task+(1|indiv)+(1|task:dist)+(1|dist:indiv))
>
> I doubt that all of them actually describe correctly what I want the model
> to answer...
>
> I did not find any directly related comment in the R help.
>
> Thank you for your attention and for any help you may provide.
>
> --
>
> ______________________________________________
> R-help@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.
>


-- 

Bert Gunter
Genentech Nonclinical Biostatistics

Internal Contact Info:
Phone: 467-7374
Website:
http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm

	[[alternative HTML version deleted]]