[R] Subsetting a data frame by dropping correlated variables

Juliet Hannah juliet.hannah at gmail.com
Thu Apr 28 04:33:27 CEST 2011

The 'findCorrelation' function in the caret package may be helpful.

On Tue, Apr 19, 2011 at 3:10 PM, Rita Carreira <ritacarreira at hotmail.com> wrote:
> Hello R Users!
> I have a data frame that has many variables, some with missing observations, and some that are correlated with each other. I would like to subset the data by dropping one of the variables that is correlated with another variable that I will keep int he data frame. Alternatively, I could also drop both the variables that are correlated with each other. Worry not! I am not deleting data, I am just finding a subset of the data that I can use to impute some missing observations.
> I have tried the following statement
> dfQuc <- dfQ[ , sapply(dfQ, function(x) cor(dfQ, use = "pairwise.complete.obs", method ="pearson")<0.8)]
> but it gives me the following error:
> Error in `[.data.frame`(dfQ, , sapply(dfQ, function(x) cor(dfQ, use = "pairwise.complete.obs",  :
>  undefined columns selected
> Since I have several dozen data frames, it is impractical for me to manually inspect the correlation matrices and select which variables to drop, so I am trying to have R make the selection for me. Does any one have any idea on how to accomplish this?
> Thank you very much!
> Rita ===================================== "If you think education is expensive, try ignorance."--Derek Bok
>        [[alternative HTML version deleted]]
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

More information about the R-help mailing list