Firstly, check your data and DCA analysis steps to trust your analysis. you should use longest gradient,
when you deciding to ordination method. Your longest gradient is on the 2nd and 3rd axis, for this reason unimodel methods suitable for your data.
For more details:
Multivariate Analysis of Ecological Data using CANOCO 5 Read more at http://www.cambridge.org/tr/academic/subjects/life-sciences/ecology-and-conservation/multivariate-analysis-ecological-data-using-canoco-5-2nd-edition#xUDwKD2I0YRri01f.99
"The gradient length measures the beta diversity in community composition (the extent of species turnover) along the individual independent gradients (ordination axes). Now you locate the largest value (the longest gradient) and if that value is larger than 4.0, you should use unimodal methods (DCA, CA, or CCA). Use of a linear method would not be appropriate, since the data are too heterogeneous and too many species deviate from the assumed model of linear response (see also Section 3.2). On the other hand, if the longest gradient is shorter than 3.0, the linear method is probably a better choice (not necessarily, see Section 3.4 of Ter Braak & Smilauer ˇ 2002). In the range between 3 and 4, both types of ordination methods work reasonably well"
Multivariate Analysis of Ecological Data using CANOCO,
Jan Leps and Petr Smilauer
But you can still use RDA if you want to, after a transformation...
"Alternatively, if your data are heterogeneous, but you still want to use linear ordination methods (PCA, RDA), apply them on Hellinger transformed species composition data to calculate ordination based on Hellinger distances (as recommended e.g. by Legendre & Gallagher (2001)). "
link: http://www.davidzeleny.net/anadat-r/doku.php/en:ordination
"Alternatively, if your data are heterogeneous, but you still want to use linear ordination methods (PCA, RDA), apply them on Hellinger transformed species composition data to calculate ordination based on Hellinger distances (as recommended e.g. by Legendre & Gallagher (2001)).
" Multivariate Analysis of Ecological Data using CANOCO,
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Graphs