R help - Oct 2014 - [vegan] Error in as.vector(x, mode) : , cannot coerce type 'builtin' to vector of type 'any' when performing anova on CCA objects

Hi there,

i have three dataframes, which have the same structure (data.frame, 358 
observations of 340 variables, every column is "num"eric), and are 
basically submatrices of a parental dataset.

I can perform a CCA on all of them (with the explanatory dataset being 
"abio")

/cca1_ab <- cca(df1~., data=abio)/

I can also perform an anova on all three cca-derived values

/anova(cca1_ab)/

However, if i do

/sig1_ab<-anova(cca1_ab, by="term", perm=200)/

which i believe gives me confidence values for the fitting of the 
explanatory variables, only one of the cca-derived values gives an 
unexpected

Error in as.vector(x, mode) : ,  cannot coerce type 'builtin' to vector 
of type 'any'

The other two are working fine. Its hard to come up with an explanation, 
as the datasets look and behave the same otherwise.

Any idea why this could happen?

I am sorry for not providing data for reproduction, as the data sets are 
pretty large.

-- 
Tim Richter-Heitmann (M.Sc.)
PhD Candidate



International Max-Planck Research School for Marine Microbiology
University of Bremen
Microbial Ecophysiology Group (AG Friedrich)
FB02 - Biologie/Chemie
Leobener Stra?e (NW2 A2130)
D-28359 Bremen
Tel.: 0049(0)421 218-63062
Fax: 0049(0)421 218-63069


	[[alternative HTML version deleted]]