[R-sig-eco] interaction effect in capscale, how to calculate

[Gian Maria Niccolò Benucci]

Hello sig-r-eco community,

I would love to have some insights on my interpretation of capscale() and
how to assess the variance explained by the interaction effect.

Imagine a model like this: Var1 + Var2 + Var1:Var2

> RsquareAdj(capscale(otu_table ~ Var1 + Var2 + Var1:Var2, metadata,
distance = "bray"))$adj.r.squared
[1] 0.281792

Then I can obtain the variance of the main factors

> RsquareAdj(capscale(otu_table ~ Var1 , metadata, distance =
"bray"))$adj.r.squared
[1] 0.1270805

> RsquareAdj(capscale(otu_table ~ Var2, metadata, distance =
"bray"))$adj.r.squared
[1] 0.09308548

Then, is this the right way to calculate the Adj.R2 for the interaction?

> RsquareAdj(capscale(otu_table~ Var1:Var2 + Condition(Var1) +
Condition(Var2), metadata, distance = "bray"))$adj.r.squared
[1] 0.05174793

However, if I sum the variances altogether I do not get the variance
explained by the full model
0.09308548 + 0.1270805 + 0.05174793 = 0.2719139

I looked online but I could not find any decent explanation of this.
Thank you for your help,

-- 
Nico

*- Do not print this email unless you really need to. *
*Save paper and protect the environment! -*

[[alternative HTML version deleted]]

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

[R-sig-eco] DCCA in R?

[Jonathan Gordon]

Hello,

I’m aiming to perform a detrended canonical correspondence analysis on a pollen 
sequence, to create beta diversity curves for pollen sequences through time. An 
example of this being done is in Felde (2019) 
. As far as I can 
tell, DCCA can’t be done in R packages such as vegan, and can only be completed 
in Canoco. I’m keen not to use Canoco because it's not open access and the 
processes behind the interface are obscured, making for a non-repeatable 
methodology. Please could you advise any way for me to perform a DCCA to obtain 
my desired results, or of a different method?

Best wishes,
Jonny 
[[alternative HTML version deleted]]

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

Re: [R-sig-eco] DCCA in R?

[Peter Solymos]

Jonathan,

Have you checked ?vegan::decorana (it is also mentioned in the vignette on
p 2: https://cran.r-project.org/web/packages/vegan/vignettes/intro-vegan.pdf
)

Cheers,

Peter

On Thu, Nov 5, 2020 at 11:03 AM Jonathan Gordon 
wrote:

> Hello,
>
> I’m aiming to perform a detrended canonical correspondence analysis on a
> pollen sequence, to create beta diversity curves for pollen sequences
> through time. An example of this being done is in Felde (2019) <
> https://link.springer.com/article/10.1007/s00334-019-00726-5>. As far as
> I can tell, DCCA can’t be done in R packages such as vegan, and can only be
> completed in Canoco. I’m keen not to use Canoco because it's not open
> access and the processes behind the interface are obscured, making for a
> non-repeatable methodology. Please could you advise any way for me to
> perform a DCCA to obtain my desired results, or of a different method?
>
> Best wishes,
> Jonny
> [[alternative HTML version deleted]]
>
> ___
> R-sig-ecology mailing list
> R-sig-ecology@r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
>


-- 
Péter Sólymos, PhD
Senior Statistical Ecologist
soly...@ualberta.ca 780-492-8534
Alberta Biodiversity Monitoring Institute http://www.abmi.ca
Boreal Avian Modelling Project http://www.borealbirds.ca

[[alternative HTML version deleted]]

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