You report a difficulty with -ranksum- but do not
say what it is.
-livbirth- is numeric.
-randgrp- should contain two (and only two)
distinct categories. If this is not true, then
it is likely to be the root of any problem.
This follows from the essence of the test, and
is not a Stata issue.
Otherwise:
What did you expect?
What did Stata do or say?
If not obvious otherwise, why this is a difficulty?
Nick
[email protected]
P chrisman
> I am having difficulty using ranksum. The code I used is ranksum
> livbirth, by(randgrp). I also tried
>
> destring numpreg livbirth, generate(numpreg2 livbirth2)
> numpreg already numeric; no generate
> livbirth already numeric; no generate
>
> . destring randgrp, generate(randgrp2)
> randgrp contains non-numeric characters; no generate
>
> Perhaps the solution to my problem is apparent, but I am not skilled
> enough with Stata to see it. Any help is appreciated.
*
* 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/
