[R] list contingency tables

[Bert Gunter]

Yes, exactly (heh, heh).

?fisher.test

is probably what is wanted.

For arbitrary rxc tables with fixed marginals, this is a difficult problem.
Mehta's efficient network algorithm to solve it can be found by a web
search on "algorithm for Fisher exact test."

-- Bert



On Fri, Nov 9, 2018 at 12:36 PM David Winsemius <dwinsemius using comcast.net>
wrote:

> Seems like you are trying to recreate the calculations needed to perform
> an exact test. Why not look at the code for that or even easier, just
> use the function.
>
> --
>
> David.
>
> On 11/8/18 8:05 PM, li li wrote:
> > Hi all,
> >    I am trying to list all the 4 by 2 tables with some fixed margins.
> >    For example, consider 4 by 2 tables with row margins 1,2,2,1 and
> > column margins 3,3. I was able to do it using the code below. However,
> > as seen below, I had to first count the total number of tables with
> > the specific row margins and column margins in order to create space
> > to store the tables.
> > Is there a way to skip the step of counting the number of tables?
> >    Also, wanted to avoid for loops as much as possible since it can be
> > extremely slow and inefficient.
> >     Thanks so much in advance for you insight and help.
> >         Hanna
> >
> >
> >
> >> library(gtools)
> >> A <- permutations(n=4,r=2,v=0:3, repeats.allowed=TRUE)
> >> B <- apply(A, 1, sum)
> >> rmg <- c(1,2,2,1)
> >> cmg <- c(3,3)
> >> m1 <- t(A[which(B==1),])
> >> m2 <- t(A[which(B==2),])
> >> m3 <- t(A[which(B==2),])
> >>
> >> ##count number of tables with row margins 1,2,2,1 and column margins
> 3,3.
> >> num <- 0
> >> for (i in 1:ncol(m1)){
> > +     for (j in 1:ncol(m2)){
> > +         for (k in 1:ncol(m3)){
> > +             M <- t(cbind(m1[,i], m2[,j], m3[,k]))
> > +             M1 <- rbind(M, cmg-apply(M,2,sum))
> > +             num <- num+(sum(M1[4,] < 0) == 0)
> > +         }}}
> >>
> >> #create space to store the tables
> >> C <- array(NA, dim=c(4,2,num))
> >>
> >> # list all the tables with fixed margins
> >> num <- 0
> >> for (i in 1:ncol(m1)){
> > +     for (j in 1:ncol(m2)){
> > +         for (k in 1:ncol(m3)){
> > +             M <- t(cbind(m1[,i], m2[,j], m3[,k]))
> > +             M1 <- rbind(M,cmg-apply(M,2,sum))
> > +             if (sum(M1[4,] < 0) == 0) {
> > +                 num <- num+1
> > +                C[,,num] <- M1
> > +             }
> > +         }}}
> >> C
> > , , 1
> >
> >       [,1] [,2]
> > [1,]    0    1
> > [2,]    0    2
> > [3,]    2    0
> > [4,]    1    0
> >
> > , , 2
> >
> >       [,1] [,2]
> > [1,]    0    1
> > [2,]    1    1
> > [3,]    1    1
> > [4,]    1    0
> >
> > , , 3
> >
> >       [,1] [,2]
> > [1,]    0    1
> > [2,]    1    1
> > [3,]    2    0
> > [4,]    0    1
> >
> > , , 4
> >
> >       [,1] [,2]
> > [1,]    0    1
> > [2,]    2    0
> > [3,]    0    2
> > [4,]    1    0
> >
> > , , 5
> >
> >       [,1] [,2]
> > [1,]    0    1
> > [2,]    2    0
> > [3,]    1    1
> > [4,]    0    1
> >
> > , , 6
> >
> >       [,1] [,2]
> > [1,]    1    0
> > [2,]    0    2
> > [3,]    1    1
> > [4,]    1    0
> >
> > , , 7
> >
> >       [,1] [,2]
> > [1,]    1    0
> > [2,]    0    2
> > [3,]    2    0
> > [4,]    0    1
> >
> > , , 8
> >
> >       [,1] [,2]
> > [1,]    1    0
> > [2,]    1    1
> > [3,]    0    2
> > [4,]    1    0
> >
> > , , 9
> >
> >       [,1] [,2]
> > [1,]    1    0
> > [2,]    1    1
> > [3,]    1    1
> > [4,]    0    1
> >
> > , , 10
> >
> >       [,1] [,2]
> > [1,]    1    0
> > [2,]    2    0
> > [3,]    0    2
> > [4,]    0    1
> >
> > ______________________________________________
> > R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> > 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.
>
> ______________________________________________
> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.
>

	[[alternative HTML version deleted]]