Helene, You will have to give us more information, such as your system/versions and a small reproducible example. We try to stress that questions are more easily answered when there are a lot of specific details given and a reproducible case can be tested.
Here are two comments though: 1. The quadratic terms probably are not showing up because you are not using a proper model formula for the task. See: http://cran.r-project.org/doc/manuals/R-intro.html#Formulae-for-statisti cal-models Specifically, the part that says "I(M): Insulate M. Inside M all operators have their normal arithmetic meaning, and that term appears in the model matrix. " is important. So, as an example from ?rda: x <- rda(Species ~ (Sepal.Length+Sepal.Width)^2 + Sepal.Width^2, data = iris) would not work for the squared term, but x <- rda(Species ~ (Sepal.Length+Sepal.Width)^2 + I(Sepal.Width^2), data = iris) would. 2. RDA is fitting models at or between LDA and QDA. So a QDA model with quadratic terms would be quartic discriminant analysis. Of course, there are no rules against this, but high order polynomials can do weird things in the tail (which would be the edges of the space defined by your training data). If your data are that nonlinear, there are much better ways of classifying data. I'd suggests getting a copy of Hastie et all (2001) or MASS. Max -----Original Message----- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of MORLON Sent: Monday, February 26, 2007 7:14 PM To: r-help@stat.math.ethz.ch Subject: [R] RDA and trend surface regression Dear all, I'm performing RDA on plant presence/absence data, constrained by geographical locations. I'd like to constrain the RDA by the "extended matrix of geographical coordinates" -ie the matrix of geographical coordinates completed by adding all terms of a cubic trend surface regression- . This is the command I use (package vegan): >rda(Helling ~ x+y+x*y+x^2+y^2+x*y^2+y*x^2+x^3+y^3) where Helling is the matrix of Hellinger-transformed presence/absence data The result returned by R is exactly the same as the one given by: >anova(rda(Helling ~ x+y) Ie the quadratic and cubic terms are not taken into account I hope you can help me with that: "how can I perform a RDA on an extended matrix of geographical coordinates in R?". Thank you very much in advance, Helene Morlon University of California, Merced [EMAIL PROTECTED] [[alternative HTML version deleted]] ______________________________________________ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. ---------------------------------------------------------------------- LEGAL NOTICE\ Unless expressly stated otherwise, this messag...{{dropped}} ______________________________________________ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
