[R-sig-eco] RDA

[Richards, Christina]

Thank you! that is exactly what we need.

Christina Richards, Ph.D.
University of South Florida
Department of Integrative Biology
4202 East Fowler Avenue SCA 127
NES 107 (shipping)
Tampa, FL 33620
(813)974-5090
(813)974-3263 FAX
http://www.ecologicalepigenetics.com
Twitter: @EcolEpig
Facebook: Ecological Epigenetics
________________________________________
From: Jari Oksanen <jari.oksanen at oulu.fi>
Sent: Thursday, November 26, 2015 1:24 PM
To: Richards, Christina
Cc: Marcelino de la Cruz; r-sig-ecology at r-project.org; Robertson, Marta; Verhoeven,     Koen; Alvarez, Mariano; Foust, Christy
Subject: Re: [R-sig-eco] RDA

> On 26 Nov 2015, at 17:27 pm, Richards, Christina <clr at usf.edu> wrote:
>
> Hello!
>
> That is very helpful and seems to work! Thank you!!
>
> I did not realize we could use raw data in capscale, is this true only because it is conditioning variables? At any rate it recapitulates our analysis using partial mantel in 2 species with 2 different results (one significant, the other not), so I'm inclined to believe its doing something similar.
>
If you supply raw community matrix (observations times species), capscale() will internally turn it into dissimilarities using specified distance= method (defaults “euclidean”). You should verify that the selected distance= method is the one you need. The variables on the right-hand-side of the formula must be in “raw” (observations times variables) format. They cannot be distances.

Cheers, Jari Oksanen

> ___
> From: Marcelino de la Cruz <marcelino.delacruz at upm.es>
> Sent: Wednesday, November 25, 2015 3:28 AM
> To: Richards, Christina; r-sig-ecology at r-project.org
> Subject: Re: [R-sig-eco] RDA
>
> Hi Christina,
>
> I think this could work:
>
> You should combine the *raw* y and z (i.e.not the Euclidean matrices) in
> the same data.frame (e.g. "yz"), and call capscale like this:
>
> capscale (x ~y1+y2+...+yn + Condition(z1+z2+...+z80), data=xy)
>
>
> Cheers!
>
> Marcelino
>
>
>
> --
> Marcelino de la Cruz Rot
> Depto. de Biología Y Geología
> Universidad Rey Juan Carlos
> Móstoles España
>
>
> El 24/11/2015 a las 22:11, Richards, Christina escribió:
>>
>>
>> Hello!
>>
>>
>> We are trying to do a partial RDA with 3 matrices but our x matrix has a lot of missing data. We could use instead distance matrices which imputed missing data, but when we try to use capscale and the euclidean matrices, it seems we have to use the formula x~y + condition (z) and we cannot use a matrix of values for z.  We would like to identify the the effect of y on x with z partitioned out where:
>>
>>
>> x= dataframe of dna methylation with individuals listed in column 1 and 0/1 data across ~80 columns
>>
>> y= habitat for each individual
>>
>> z= dataframe of genetic loci with individuals listed in column 1 and 0/1 data across ~80 columns
>>
>>
>> Christina Richards, Ph.D.
>> University of South Florida
>> Department of Integrative Biology
>> 4202 East Fowler Avenue SCA 127
>> NES 107 (shipping)
>> Tampa, FL 33620
>> (813)974-5090
>> (813)974-3263 FAX
>> http://www.ecologicalepigenetics.com
>> Twitter: @EcolEpig
>> Facebook: Ecological Epigenetics
>>
>>      [[alternative HTML version deleted]]
>>
>> _______________________________________________
>> R-sig-ecology mailing list
>> R-sig-ecology at r-project.org
>> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
>>
>
> _______________________________________________
> R-sig-ecology mailing list
> R-sig-ecology at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology