[R] calculate column means when missing data is present

[Denver XU]

colMeans(X,na.rm=T)
?colMeans




2007/11/27, Luke Neraas <lukasneraas.r at gmail.com>:
> # Hello,
>
> # I have a matrix that contains some missing values denoted by NA.
> # I would like to calculate the mean for each column and not have the
> # NA values included.  here is a sample matrix  "X" below.
>
>
> c1 <- c(1,4,3,2,NA,2,5,6,4,2)
> c2 <- c(1,3,6,NA,NA,2,9,6,1,2)
> c3 <- c(2,4,2,NA,4,2,NA,6,3,5)
> c4 <- c(2,6,4,NA,4,2,NA,6,1,5)
> c5 <- c(2,3,2,NA,4,2,9,6,NA,5)
>
> X<-cbind(c1,c2,c3,c4,c5)
>
> X
>
> # I have tried a variety of methods to calculate the Column means but each time
> # i do not get the result i am looking for
>
> result<-colMeans(X)  # only returns a mean of NA
>
>
> X <- X[!is.na(X)]    # Effectively removes the NA values but now I
> cannot calculate Column Means
>
> #  Below is the result of the column means I am looking for
>
> result
>        c1   c2    c3   c4    c5
>  [1,] 3.22 3.75  3.5  3.75 4.125
>
>
> # any help or ideas would be greatly appreciated
>
> # thanks in advance
>
> Luke Neraas
>
> lukasneraas.r at gmail.com
>
> University of Alaska Fairbanks
> School of Fisheries and Ocean Sciences
> 11120 Glacier Highway
> UAF Fisheries Division
> Juneau, AK 99801
>
> ______________________________________________
> 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.
>