Re: st: Weighted number of observations

[Richard Williams <Richard.A.Williams.5@nd.edu>]

At 10:35 AM 7/30/2004 -0700, Friedrich Huebler wrote:

> According to -tab-, the weighted number of observations=1 is about
> 16.9. According to -tabstat-, the number is 50950. With -collapse- we
> get the same result as with -tab-.
To add to the mystery:

. tabstat foreign [aw=weight], stat(count)

    variable |         N
-------------+----------
     foreign |        74
------------------------

. tabstat foreign [aw=weight], stat(mean)

    variable |      mean
-------------+----------
     foreign |  .2280254
------------------------

. tabstat foreign [aw=weight], stat(sum)

    variable |       sum
-------------+----------
     foreign |     50950
------------------------

So, the weighted N is 74, the mean is .228 (both of these are consistent 
with other results) but the sum is 50950.  It appears that, unlike the 
other stats, the sum is not calculated by first rescaling back to the 
original sample size, e.g. aweights and fweights give you the same result 
when computing the sum using tabstat.

I never want to be so bold as to call something an error, but I too am 
puzzled by this behavior.

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc

*
*   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/