[R] "mvr" function

Jim BRINDLE j_brindle at hotmail.com
Wed Jun 1 23:02:56 CEST 2005


Hello,

I am trying to understand how to utilize the "mvr" function in the pls 
Package of R.  I am utilizing the R "pls Package" document dated 18 May 2005 
as guidance.  My data set consists of a 12 x 12 data frame created from 
reading in a table of values.  I have read the data in via the command:

volumes <- read.table("THA_vol.txt", header = TRUE)

and then created a data.frame called "vol".  My response variable is in the 
last column of the "vol" data frame and my dependent variables are in 
columns 1 through 11.

To familiarize myself with this approach I have utilized the NIR data set 
(included in the pls Package).  I get the following command to work with the 
NIR data set:

NIR.pcr <- pcr(y ~ X,6,data=NIR,validation="CV")

However, when I run the following script which effectively substitutes my 
data set (& modify variable names accordingly) into the above equation:

y <- vol[,12]
X <- vol[,1:11]
ans.pcr <- pcr(y ~ X,6,data=vol,validation="CV")


I get the following error:

Error in model.frame(formula, rownames, variables, varnames, extras, 
extranames,  :
       invalid variable type

I have looked at the NIR data set in the pls Package and tried to see how it 
"structurally" differs from my data-set "structure" (other than in its 
size).

Does anyone have any insight they might be willing to share?

Thank you kindly.

- Jim




More information about the R-help mailing list