Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: summary tables for categorical variables


From   Nick Cox <[email protected]>
To   "[email protected]" <[email protected]>
Subject   Re: st: summary tables for categorical variables
Date   Wed, 12 Feb 2014 00:26:55 +0000

I don't know what -tabw- is, but I didn't recommend it.

-tabm- from -tab_chi- offers the options of -tabulate-. The help explains:

tabulate_options are options allowed with tabulate varname1 varname2.

Consider

set obs 100
forval j = 1/9 {
     gen y`j' = ceil(10 * runiform())
}
tabm y*, row
tabm y*, col

Nick
[email protected]

On 11 February 2014 22:58, Donald Spady <[email protected]> wrote:

> Nick. Thanks for the fast response.  Your suggestion of mrtab is close, but not quite what I need.  mrtab puts the variables down the left side of the table, but only gives a summary of the frequency of the responses.  I want to have (for e.g. 6 columns: 1 for the variable name and 5 for the possible responses (e.g. SA A N D SD).  I dont see any option within mrtab to do that.
>   I looked at tabw which is much closer to what is needed, but it does not give the option of say percentage rather than frequency. I know that is nitpicking, but Stata is so extensible I wonder if anyone has looked at this.

On Feb 11, 2014, at 1:40 PM, Nick Cox <[email protected]> wrote:

>> Sounds like
>>
>> -mrtab- (SJ)
>>
>> -tabm- (-tab_chi- on SSC)

On 11 February 2014 20:23, Donald Spady <[email protected]> wrote:

>>> I want to create a table for categorical variables that is something like tabstat where the variable names are in a left hand column and, instead of statistics in the columns to the right, I want the contents of the categories that the variable contains.
>>> For example
>>> Varname "likeDon" SA:10, A:5, N:3, D:1 SD 2 Miss/NA: 2
>>> varname "likeNick" SA:50, A;20, N:3, D:12, SD: 0 Miss/NA:4
>>> varname "likeSue"  and so on
>>> where SA A N D and SD are the possible responses.
>>>
>>> Is there anything in Stata that can do this. If so, what and how?

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index