R help - Jul 2009 - table () for more variables

Dear  All,

I want to create a table for several variables. As example. I have a
dataframe with following data:

Gender            transport      driving
1                     0                 1
0                     1                 0
1                     0                 1

Now I want to create a table in the following form:

                                   Gender
                                  1         0
Transport 1                  2         0
               0                 0         1
Driving     1                  2         0
               0                  0         1

In which the different percentages are being calculated (row/column). I have
tried using ftable() but did not give the desired result (There are a lot of
variables and the format makes it impossible to interpret).

Is there anyone who can help me with this problem?

Thanks in advance.
Kind regards,

John

	[[alternative HTML version deleted]]

On Jul 3, 2009, at 1:10 PM, John Lipkins wrote:
> Dear  All,
>
> I want to create a table for several variables. As example. I have a
> dataframe with following data:
>
> Gender            transport      driving
> 1                     0                 1
> 0                     1                 0
> 1                     0                 1
>
> Now I want to create a table in the following form:
  gtd <- read.table(textConnection("Gender            transport       
driving
  1                     0                 1
  0                     1                 0
  1                     0                 1
  "), header=TRUE)
>
>                                   Gender
>                                  1         0
> Transport 1                  2         0
>               0                 0         1
> Driving     1                  2         0
>               0                  0         1
That's really two tables stacked on top of each other. The sum of its  
entries is 2n.

with(gtd, rbind(
                 xtabs( ~ transport + Gender) ,
                 xtabs( ~ driving + Gender)
        )       )
   0 1
0 0 2
1 1 0
0 1 0
1 0 2
>
> In which the different percentages are being calculated (row/column).
Percentages? Don't see any in the requested output. Maybe you really  
want CroosTables in the gmodels package.
> I have
> tried using ftable() but did not give the desired result (There are  
> a lot of
> variables and the format makes it impossible to interpret).
You could think about using summary or one of its substitutes inside  
an apply construction.

David Winsemius, MD
Heritage Laboratories
West Hartford, CT

On Jul 3, 2009, at 12:10 PM, John Lipkins wrote:
> Dear  All,
>
> I want to create a table for several variables. As example. I have a
> dataframe with following data:
>
> Gender            transport      driving
> 1                     0                 1
> 0                     1                 0
> 1                     0                 1
>
> Now I want to create a table in the following form:
>
>                                   Gender
>                                  1         0
> Transport 1                  2         0
>               0                 0         1
> Driving     1                  2         0
>               0                  0         1
>
> In which the different percentages are being calculated (row/ 
> column). I have
> tried using ftable() but did not give the desired result (There are  
> a lot of
> variables and the format makes it impossible to interpret).
>
> Is there anyone who can help me with this problem?
>
> Thanks in advance.
> Kind regards,
>
> John
John,

Take a look at the 'catspec' package by John Hendrickx on CRAN. There  
is a function in there called 'ctab', which if memory is correct, will  
do what you want. John had originally posted his code here:

   https://stat.ethz.ch/pipermail/r-help/2003-February/030400.html

and it has been updated to some extent in the package since then.

HTH,

Marc Schwartz