[R-sig-eco] repeated measures

[Leonardo Salas]

Steve,

The best way to do what you want is with package unmarked, which has the capacity to fit prevalence (presence/absence) models with covariates for both detection and presence, so long you do have a repeated measures sample.  Another option is a Bayesian approach, but it's much easier to do this with unmarked.

Leo

-----Original Message-----
Date: Fri, 12 Nov 2010 11:19:23 -0500
From: Steve_Friedman at nps.gov
To: r-sig-ecology at r-project.org
Subject: [R-sig-eco] repeated measures
Message-ID:
        <OF025F4F8B.32F45226-ON852577D9.0058ECBF-852577D9.0059AA5F at nps.gov>
Content-Type: text/plain; charset=US-ASCII


Hi,
This is a question regarding technique rather than an R specific issue.  I
have been asked to evaluate a 30+ year long term continuous survey of bird
presence/absence data that has an associated ocular estimate of the
vegetation community percent coverage.  The data are organized by
subpopulations (5), and by year ( 1991 - present).  We are interested in
gaining understanding on whether bird presence is 1) related to vegetation
community cover and 2) whether that relationship is variable over the
period of record.  Ultimately, I can associate management to this, but that
data has not be pulled together yet for this survey.

My first thought was to simply look to a clustering (vegetation conditions)
and nmds  (veg condition and bird presence/absence) to examine which sites
were more similar given the vegetation community. This analysis would help
us understand which sites were similar/dissimilar from one another.
Following this I had intended to repeat that analysis using year as a
grouping variable to see if the clusters change. This would then provide
the basis for a trajectory analysis.

Ok, so that might be rather very simple, I'm now considering a repeated
measures approach, but do not have much experience here.  Since every site
is the same in all years, what changes is the bird count and perhaps the
vegetation community coverage estimates.

Can someone let me know if this alternate approach is a better approach and
how to conduct the analysis in R?  If not what methodology do you suggest?

Thanks very much.  If additional information is needed I can provide it,
but I didn't want to fill mail boxes with unnecessary info at this time.

Thanks
Steve

Steve Friedman Ph. D.
Spatial Statistical Analyst
Everglades and Dry Tortugas National Park
950 N Krome Ave (3rd Floor)
Homestead, Florida 33034

Steve_Friedman at nps.gov
Office (305) 224 - 4282
Fax     (305) 224 - 4147



------------------------------

Message: 2
Date: Fri, 12 Nov 2010 17:17:55 -0800 (PST)
From: Paulo Prado <prado at ib.usp.br>
To: r-sig-ecology at r-project.org
Subject: Re: [R-sig-eco] Fit log-series to species-rank abundance
Message-ID: <1289611075557-5734514.post at n2.nabble.com>
Content-Type: text/plain; charset=us-ascii


Dear Guillem,

May 1975 (in Patterns of Species Abundance and Diversity. In M. L. Cody & J.
M. Diamond (Eds.)) gives the recipe to fit expected curves of a SAD model in
rank-abundance plots. The trick is to find the inverse function of the CDF
of the SAD model. A simple solution in R is to calculate the cumulative
number of species predicted by the logseries and to use this values as
independente variables for the function splinefun, to create a function that
plots the expected curve of the model in the rank-abundance plot. Please
find attached a code that seems to do the job at least for visual comparison
of models. There are also the PDF function  for the logseries, and a
function to fit it that returns the log-likelihood and the AIC of the model.

Hope it helps

Best Wishes

Paulo Prado

http://r-sig-ecology.471788.n2.nabble.com/file/n5734514/logseries.r
logseries.r
--
View this message in context: http://r-sig-ecology.471788.n2.nabble.com/Fit-log-series-to-species-rank-abundance-tp5729089p5734514.html
Sent from the r-sig-ecology mailing list archive at Nabble.com.



------------------------------

_______________________________________________
R-sig-ecology mailing list
R-sig-ecology at r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology


End of R-sig-ecology Digest, Vol 32, Issue 12