Hi,
 I found the book Mixed effects models and Extensions in Ecology With
R by Zuure et al. Was useful.
They have a good example of model comparison.
Rebecca

On Wed, Apr 21, 2010 at 2:00 AM, Helen Bothwell <[email protected]> wrote:
> In working with AICc model averaging and selection, I am not sure what the
> precedence is for choosing a subset of models to compare.  We are
> investigating genetic loci under supposed adaptive selection pressure from
> environmental variables.  We have no prior expectations of which specific
> variables may be influencing certain loci and can not a priori reduce
> models for comparison.  Our data set includes a large number of plausible
> explanatory environmental variables.  We initially compared a subset of
> models with delta AIC values ranging from 0-10.  I have found information
> saying that delta AIC values from 0-2 indicate that a given model should
> be considered within the range of plausible models for the set under
> investigation.  Coding in R for a given locus, when I change the input
> call for the subset of deltas to compare (I've tried 10, 5, and 3) the
> Deviance, AICc, and Delta of the various models do not change, however the
> weights given to the various models do change as do the values of Relative
> Variable Importance.  For example, with input delta <10, the best model
> weight is 0.03, whereas it is 0.074 with input delta <3.  Is there a
> precedence for how many models to compare, a subset Delta AICc cut-off
> line for model comparison?  Any feedback is much appreciated!
>
> Sincerely,
> Helen Bothwell
>

Reply via email to