[R-sig-Geo] correlation betwee two grids acounting for univariate spatial autocorrelation, how to do it?

[Seth Flaxman]

Hi Jesús.

I think of this as something of an open research problem, so I'm
curious to hear what others have to say. I looked at the reference you
sent (which is new to me, looks interesting!)

Is your original data a spatial point pattern which you've smoothed
into a map (as in spatial point processes)? Or do you have variables
observed for spatial regions (as in geostatistics)?

Seth

On Thu, Feb 20, 2014 at 1:51 PM, Jesús Muñoz <jmunoz at rjb.csic.es> wrote:
> Dear colleagues,
>
> I needed to measure the association degree (and ideally its p-value) between
> two maps, one representing richness of European bryophytes and the other
> vascular plant richeness. From the maps it is clear the two patterns are
> reversed: bryophytes 'rule' in the north, and vascular plant richness is
> higher in  southern Europe.
>
> I have used isodata algorithm followed by a Maximum-likelihood
> classification to generate a map showing four different areas in Europe
> (lowbryo-lowvasc, lowbryo-highvasc, highbryo-lowvasc, and
> highbryo-highvasc). Additionally, I would like to run a correlation analysis
> but corrected for the univariate spatial correlation of each variable
> (bryophytes and vascular plant richness); a global correlation map-to-map is
> meaningless here.
>
> I found a statistic that would suit my needs (Lee, S.-I. 2001. Developing a
> bivariate spatial association measure: An integration of Pearson's r and
> Moran's I. Journal of Geographical Systems 3(4): 369-385). It is implemented
> in 'The Map Comparison Kit' (http://www.riks.nl/mck/), but it return values
> outside the -1 to 1 values, which makes me think there is something wrong in
> the code or the statistic.
>
> Can somebody guide me to a R package allowing me to measure the association
> between these two grids?
>
> thanks in advance,
>
> Jesús
>
>
>
>
>
> *************************************************************************
>
> Jesús Muñoz PhD            e-mail: jmunoz at rjb.csic.es
>
> Real Jardín Botánico (CSIC)
>
> C/ Claudio Moyano 1        tlf. +34 91 420 3017
>
> E-28014 Madrid             fax. +34 91 420 0157
>
> ESPAÑA (Spain)
>
>
>
> http://www.masterenbiodiversidad.org
>
>
>
> http://www.rjb.csic.es/jardinbotanico/jardin/contenido.php?Pag=413&tipo=cien
> tifico&cod=66
>
>
>
> KRAKEN research group (environmental modelling, data processing & analysis):
>
>                             http://www.unex.es/investigacion/grupos/kraken
>
>
>
> SYNTHESYS: EU funds short visits to our institution:
>
> http://www.synthesys.info/index.htm
>
> *************************************************************************
>
>
>
>
>
> __________ Información de ESET Endpoint Security, versión de la base de
> firmas de virus 9449 (20140220) __________
>
> ESET Endpoint Security ha comprobado este mensaje.
>
> http://www.eset.com
>
>
>         [[alternative HTML version deleted]]
>
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>