Ricardo,
Here is oneway. Note, it does give 27 combination, the combination that SAS
does not report is (a = 1, b = 1, c = 0 ==> sum = 0). I suppose you could
add a statement to drop if sum == 0.
count
set obs `=r(N) + 1'
tempfile results
tempname hold
postfile `hold' a b c freq sums using `results'
qui {
levelsof a, missing local(a)
levelsof b, missing local(b)
levelsof c, missing local(c)
foreach j of local a {
foreach k of local b {
foreach l of local c {
sum n if a != `j' & b !=`k' & c != `l'
local sums = r(sum)
local freq = r(N)
local j = abs(`j' - 1)
local k = abs(`k' - 1)
local l = abs(`l' - 1)
post `hold' (`j') (`k') (`l') (`freq') (`sums')
}
}
}
}
postclose `hold'
preserve
use `results', clear
li
restore
drop if a == .
Hope this helps,
Scott
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Ricardo Ovaldia
> Sent: Wednesday, August 17, 2005 7:04 PM
> To: [email protected]
> Subject: st: SAS like command?
>
> Dear all,
>
> SAS's proc mean with the class command expands the
> class variables creating all possible combinations
> including data with missing data. Is there a way to
> do this in Stata?
>
> Thank you,
> Ricardo.
>
> Example:
>
> Starting with these data:
>
> Obs a b c n
>
> 1 0 0 0 3
> 2 0 0 1 4
> 3 0 1 1 5
> 4 1 1 1 10
> 5 0 1 0 7
> 6 0 1 1 5
> 7 1 0 0 8
> 8 1 0 1 9
>
> The SAS command:
>
> proc means;
> class a b c;
> var n;
> output sum=tsum ;
>
> Yields:
>
>
> Obs a b c _TYPE_ _FREQ_ tsum
> 1 . . . 0 8 51
> 2 . . 0 1 3 18
> 3 . . 1 1 5 33
> 4 . 0 . 2 4 24
> 5 . 1 . 2 4 27
> 6 . 0 0 3 2 11
> 7 . 0 1 3 2 13
> 8 . 1 0 3 1 7
> 9 . 1 1 3 3 20
> 10 0 . . 4 5 24
> 11 1 . . 4 3 27
> 12 0 . 0 5 2 10
> 13 0 . 1 5 3 14
> 14 1 . 0 5 1 8
> 15 1 . 1 5 2 19
> 16 0 0 . 6 2 7
> 17 0 1 . 6 3 17
> 18 1 0 . 6 2 17
> 19 1 1 . 6 1 10
> 20 0 0 0 7 1 3
> 21 0 0 1 7 1 4
> 22 0 1 0 7 1 7
> 23 0 1 1 7 2 10
> 24 1 0 0 7 1 8
> 25 1 0 1 7 1 9
> 26 1 1 1 7 1 10
>
>
> Ricardo Ovaldia, MS
> Statistician
> Oklahoma City, OK
>
>
>
> ____________________________________________________
> Start your day with Yahoo! - make it your home page
> http://www.yahoo.com/r/hs
>
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
