Thanks. David. I also looked at that, as I have a variable called zallemps, which is the total employment on the payroll at the establishment. But when I tried both forms of denominator I got
. gen ratioprtwrk=(zmalprta+zfemprta) / (zallemps)
(40 missing values generated)
. su ratioprtwrk
Variable | Obs Mean Std. Dev. Min Max
-------------+--------------------------------------------------------
ratioprtwrk | 22411 .0631298 .1019029 .0002026 .8
. gen ratioprtwrk=(zmalprta+zfemprta) / ((zmalfulla+zfemfulla+zmalprta+zfemprta))
(40 missing values generated)
. su ratioprtwrk
Variable | Obs Mean Std. Dev. Min Max
-------------+--------------------------------------------------------
ratioprtwrk | 22411 .5385854 .0624591 .3333333 .6666667
I am pondering as to why there is a difference.
Thanks
I would add, that you may want to look, instead at the ratio...
(zmalprt+zfemprt) / (zmalfull+zfemfull+zmalprt+zfemprt)
that is, the proportion that part-time work represents as compared to
the total work. But that's something you need to decide as a
substantive matter.
--David
At 10:58 PM 6/10/2006, you wrote:
>On 6/11/06, peter harper <[email protected]> wrote:
>>Dear Statalisters
>>
>>Since the ratio of part time work, would be
>>the total of the part-time work (i.e., of the both
>>genders) over the total of the full time work of both
>>the genders, I presume I do
>>[...]
>gen ratioprtwrk=(zmalprt+zfemprt) / (zmalfull+zfemfull)
>
>Neil
>[...]
*
* 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
*
* 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/
