[R] Multidimensional contingency tables

hadley wickham h.wickham at gmail.com
Tue Apr 22 15:54:02 CEST 2008


On Tue, Apr 22, 2008 at 8:24 AM, hadley wickham <h.wickham at gmail.com> wrote:
> On Mon, Apr 21, 2008 at 9:46 PM, Robert A. LaBudde <ral at lcfltd.com> wrote:
>  > How does one ideally handle and display multidimenstional contingency
>  >  tables in R v. 2.6.2?
>  >
>  >  E.g.:
>  >
>  >   > prob1<- data.frame(victim=c(rep('white',4),rep('black',4)),
>  >  +   perp=c(rep('white',2),rep('black',2),rep('white',2),rep('black',2)),
>  >  +   death=rep(c('yes','no'),4), count=c(19,132,11,52,0,9,6,97))
>  >   > prob1
>  >    victim  perp death count
>  >  1  white white   yes    19
>  >  2  white white    no   132
>  >  3  white black   yes    11
>  >  4  white black    no    52
>  >  5  black white   yes     0
>  >  6  black white    no     9
>  >  7  black black   yes     6
>  >  8  black black    no    97
>  >
>  >  The xtabs() function doesn't seem appropriate, as it has no means of
>  >  using 'count'.
>  >
>  >  This must be a common problem.
>
>  You can also use the reshape package (http://had.co.nz/reshape)
>
>  cast(prob1, victim ~ perp, sum, value="count")
>  cast(prob1, victim ~ perp ~ death, sum, value="count")
>  cast(prob1, death + victim ~ perp, sum, value="count")

Ooops, that's using my development version.  For the currently
available version you need:

prob1 <- rename(prob1, c("count" = "value"))
cast(prob1, victim ~ perp, sum)
cast(prob1, victim ~ perp ~ death, sum)
cast(prob1, death + victim ~ perp, sum)

Hadley
-- 
http://had.co.nz/



More information about the R-help mailing list