[R] cov.mve error

Marino Taussig De Bodonia, Agnese agnese.marino09 at imperial.ac.uk
Tue Nov 2 17:43:05 CET 2010


I am trying to use the cov.mve function on a set of variables to check for outliers, before I perform PCA on them. I am using the code that I found on "Everitt (2005) An R ans S-Plus companion to multivariate analysis" but its doesn't seem to work. I wrote:

at.central<-central[,7:17]       # 7:17 are the 10 variables that I want to screen for outliers
at.central.mve<-cov.mve(central, cor=T)

I also tried what the help file says to do:

at.central.mve<-cov.rob(central, cor=T, method="mve")

Both give me the error:

Error in quantile.default(as.numeric(x), c(0.25, 0.75), na.rm = na.rm,  :  missing values and NaN's not allowed if 'na.rm' is FALSE
In addition: Warning message: In quantile(as.numeric(x), c(0.25, 0.75), na.rm = na.rm, names = FALSE) : NAs introduced by coercion

My dataset has no NAs, so what does this mean?? Something to do with the "quantile.used=" argument?

Thanks in advance for your time,


More information about the R-help mailing list