This is good technique, but also a
re-invention of what is already provided
by -contract, zero-.
On the original question, see also -groups-
from SSC.
Nick
[email protected]
Joseph Coveney
> You can get the cross-tabulation counts by using
>
> preserve
> contract religion gender age ethnicity
> list, noobs separator(0)
> restore
>
> The cell counts are in the variable _freq.
>
> --------------------------------------------------------------
> ------------------
>
> I forgot to mention that, if you suspect that some cell
> counts are zero
> (that is, if some combinations are not represented among the
> original data)
> and if you want those listed, then you would make placeholders for the
> combinations by inserting a -fillin religion gender age
> ethnicity- command
> after -contract-, fill in the missing values of _freq with zeroes, and
> then -sort- again before -list-.
*
* 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/
