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]

st: RE: Sort Two-Way Tab


From   "Martin Weiss" <[email protected]>
To   <[email protected]>
Subject   st: RE: Sort Two-Way Tab
Date   Wed, 26 May 2010 17:40:11 +0200

<>
" I
have searched specifically through -tab1-, -tab2-, -tabstat-, -table-,
and -estout-, with no clear resolution."



Suspiciously absent from your list is -ssc d fre- by Ben Jann...


HTH
Martin


-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Kyle Longest
Sent: Mittwoch, 26. Mai 2010 17:36
To: [email protected]
Subject: st: Sort Two-Way Tab

Statalist,

I am using Stata SE 11.0. I have searched through the manuals, help,
and statalist and not found a direct solution to my issue, but
apologize in advance if there is a straightforward resolution.

Problem: I would like to create a cross-tabulation of two variables
that is displayed in the sorted (by frequency) of the row variable. I
have searched specifically through -tab1-, -tab2-, -tabstat-, -table-,
and -estout-, with no clear resolution.

Description and Example: using auto.dta.

Say I was interested in the relationship between miles per gallon
(mpg) and a car's repair record (rep78). There are numerous possible
mpg's so I decide to only be concerned with the 5 most common mpg's.
[I'd like to set the analytic validity/utility aside for a moment, as
in the applied problem the desired technique is more warranted, for
various reasons, than it may be in this example.] It is easy to get a
frequency distribution of mpg in this sorted order using tab with the
sort option:

. tab mpg, sort

    Mileage |
      (mpg) |      Freq.     Percent        Cum.
------------+-----------------------------------
         18 |          9       12.16       12.16
         19 |          8       10.81       22.97
         14 |          6        8.11       31.08
         21 |          5        6.76       37.84
         22 |          5        6.76       44.59
         25 |          5        6.76       51.35
[omitted]

But now I would like to have this same distribution (order)
cross-tabulated by the levels of rep78 (across the columns). As far as
I can tell there is no way to do this with a current command. -tab-
and its derivatives do not allow the sort option. For example, any
call to tab will produce the following, which abandons the frequency
sort order of mpg:

. tab mpg rep78

Mileage |             Repair Record 1978
  (mpg) |    1         2       3          4      5 |     Total
-----------+--------------------------------+----------
        12 |    0          0       2          0     0 |         2
        14 |    0          1       2          2     0 |         5
        15 |    0          0       1          1     0 |         2
        16 |    0          1       2          1     0 |         4
        17 |    0          1       1          0     2 |         4
        18 |    1          2       2          2     2 |         9
        19 |    0          0       7          0     0 |         7
        20 |    0          0       3          0     0 |         3
        21 |    0          0       3          2     0 |         5
[ommitted]

What I am hoping is that there is a command or method to produce the
following (along with the row/column %s which are omitted for
brevity):

. command mpg rep78, option

 Mileage |             Repair Record 1978
  (mpg) |    1         2          3          4      5     |     Total
-----------+---------------------------------------+----------
       18 |    1          2          2          2          2 |         9
       19 |    0          0          7          0          0 |         7
       14 |    0          1          2          2          0 |         5
       21 |    0          0          3          2          0 |         5
[ommitted]

I have considered some manual options (e.g., using the gen option with
-tab- and then compiling  a matrix with the appropriate frequencies
and percentages) but was hoping there may be a more straightforward
solution. [I also realize that this is primarily a convenience issue
as I could feasibly copy and paste the given cross tab into the
desired order but this task can be extremely time consuming if there
sort variable has many categories].

Any assistance would be greatly appreciated,
Kyle

Kyle C. Longest
Assistant Professor
Department of Sociology
Furman University
[email protected]
eweb.furman.edu/~klongest
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

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


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