Hi all,
I am using v9.2 and trying to permute results for a Breslow-Day test
statistic, however the seed option is not 'working', as I am unable to
exactly replicate the permuted p-values. I am trying test if the
distribution of variable Y is homogeneous across a binary variable Z,
given levels of X (binary), where X is permuted.
I have tried the following commands:
xi: permute X r(chi2_bd), reps(10000) nodots nowarn seed(171): cc Z
i.Y, by(X) bd
permute X "xi:cc Z i.Y, by(X) bd" r(chi2_bd), reps(10000) nodots
nowarn seed(171)
I have also tried setting the seed before the command, using:
set seed 171
xi. permute etc
Let me know if what I am trying to achieve is possible, or where am I
going wrong.
Thanks,
Farren
*
* 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/