www.phidot.org

I just posted v1.9.4 of RMark. See What's new for a complete list of changes etc. Below is a brief summary of some changes. If you update to R 2.10 you'll need to update to this version of RMark as well. Thanks to Dave Hewitt and Andrew Paul for help with testing.

1) Added the function popan.derived which for POPAN models computes derived abundance estimates by group and occasion and sum of group abundances for each occasion.
2) The model.average.list and model.average.marklist functions were modified to use revised estimator for the unconditional standard error (eq 6.12 of Burnham and Anderson (2002)) which is now the default in MARK. To use eq 4.9 (the prior formula) set the argument
revised=FALSE.
3) Code in model.average.marklist was changed to set standard error to 0 if the variance is negative. The same is done in the var-cov matrix for the variance and any corresponding covariances. The results from RMark will now match the model average results from MARK for this case.

jlaake wrote:2) The model.average.list and model.average.marklist functions were modified to use revised estimator for the unconditional standard error (eq 6.12 of Burnham and Anderson (2002)) which is now the default in MARK. To use eq 4.9 (the prior formula) set the argument
revised=FALSE.

The formula that Jeff refers to is the same formula you find throughout the MARK 'guide' - frequently in chapters 4, and 6. For example, see section 4.5.1.

cooch wrote:

jlaake wrote:2) The model.average.list and model.average.marklist functions were modified to use revised estimator for the unconditional standard error (eq 6.12 of Burnham and Anderson (2002)) which is now the default in MARK. To use eq 4.9 (the prior formula) set the argument
revised=FALSE.

The formula that Jeff refers to is the same formula you find throughout the MARK 'guide' - frequently in chapters 4, and 6. For example, see section 4.5.1.

I just posted a revised Chapter 4, which cleans up a small issue - in earlier versions of MARK, the 'revised variance formula' was no checked as the default. It is now - but I had been using old screen images which didn't show this. I've updated the images, and added text in a couple of places to make it clear that the revised formula is the one you want to use. It is checked by default for the 'normal' interactive model averaging window.

However, as it turns out, it does not seem to be checked by default if you use the 'non-interactive' model averaging (described in the sidebar beginning on p. 47 of Chapter 4) - it should be (I've passed this along to Gary). So, if you use the non-interactive model for model-averaging, you'll probably need to manually check the `revised formula' box.