log- and z-transforming my data in R -

i'm preparing data pca, need standardize it. i've been following else's code in vegan not getting mean of 0 , sd of 1, should be.

i'm using data set called musci has 13 variables, 3 of labels identify data.

log.musci<-log(musci[,4:13],10) stand.musci<-decostand(log.musci,method="standardize",margin=2) 

when check mean=0 , sd=1...

colmeans(stand.musci) sapply(stand.musci,sd) 

i mean values ranging -8.9 3.8 , sd values listed na (for every data point in data set rather each variable). if leave out last variable in standardization, i.e.

log.musci<-log(musci[,4:12],10) 

the means don't change, sds have value of 1.

any ideas of i've gone wrong?

cheers!

you data matrix.

## sample data dat <- as.matrix(data.frame(a=rnorm(100, 10, 4), b=rexp(100, 0.4))) 

so, either convert data.frame , use sapply operate on columns

dat <- data.frame(dat) scaled <- sapply(dat, scale) colmeans(scaled) #                         b  # -2.307095e-16  2.164935e-17  apply(scaled, 2, sd) # b  # 1 1  

or use apply columnwise operations

scaled <- apply(dat, 2, scale)