Hello,
Does anyone know how to calculate z-values from odds ratios and
standard errors of odds ratios?
I have run a hugh amount of "logit..., robust or" regressions
followed by "lincom....., or", and I have posted all the r(estimate)
and r(se) to a new file. The new file thus contains one variable with
odds ratios and one variable with the standard errors of odds ratios.
How can I construct a new variable with the z-values (or some
approximation of z-values)? I thought that "gen z = ln(odds ratio) /
ln(se)" would do it but it is obviously not the right way to do it.
Best,
Yvonne
*
* 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/
