[R-sig-Geo] patial distribution of the ecological niche of cowpea,

[Soufianou Abou]

I want to model the spatial distribution of the ecological niche of cowpea, I have a set of data (environmental variables and bioclimatic) and data of presence of the varieties of cowpea.I wanted to use the software Maxent for do it; But I understood through the literature that the R software is now widely used. It is with this in mind that I would like to focus on this. By the way, I need help to understand the procedures for doing this modeling using R. 1. I would like to do a Shapiro-Wilks normality test, the null hypothesis of which is to assert that The data follow a normal distribution and where the alternative hypothesis implies an asymmetric or abnormal distribution, makes it possible to conclude that the observations are of very asymmetric distribution. 2. I would like to do a logarithmic transformation of the response data is therefore performed in order to reduce the asymmetry of the data and thus improve the power of the statistical tests.3. I would like to do a canonical redundancy analysis on all the data tables. 4. I would like to make a bidirectional progressive selection in order to select the relevant variables according to Akaike's information criterion or AIC and Of the representativeness (p-value) .5. I would like to make a progressive selection by adding, according to the adjusted R-square, in order to compare the result of the selection 6. Finally, the procedures to be followed to model the distribution of the varieties.

Best regards 
 SADDA Abou-Soufianou -------------------------------------- DoctorantUniversité Dan Dicko Dankoulodo de Maradi,120 avenue Maman Koraou,ADS, MaradiBP 465 Maradi/Niger E-mail: a.soufianou at yahoo.frGSM : (+227)96269987
	[[alternative HTML version deleted]]