Dear list, I want to run a db-RDA with "capscale" to analyse community data (a distance matrix created with "betadiv") against pcnm vectors (it will be followed by db-RDA against environmental variables and eventually variance partitioning). However, when I try to forward select PCNM vectors with the function "ordiR2step" I get an error More specifically:
dat.comm<-betadiver(species, method=22, order=FALSE, help=FALSE) pcnm72<-pcnm(dist(xycart)) dat.pcnm<-as.data.frame(scores(pcnm72))
Following the example of ordiR2step with direction = "forward"
mod0.pcnm<-capscale(dat.comm~1, dat.pcnm) mod1.pcnm<-capscale(dat.comm~., dat.pcnm) mod.step.pcnm<-ordiR2step(mod0.pcnm,scope=formula(mod1.pcnm),direction="forward",perm.max=200)
I get the following error Error in ordiR2step(mod0.pcnm, scope = formula(mod1.pcnm), direction = "forward", : the upper scope cannot be fitted (too many terms?) I would really appreciate it if someone could tell me what this error means and how to avoid it Many thanks, Marika Marika Galanidi Post-doctoral Researcher DEU, Izmir, Turkey -- View this message in context: http://r-sig-ecology.471788.n2.nabble.com/ordiR2step-error-tp7579341.html Sent from the r-sig-ecology mailing list archive at Nabble.com.