Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Permutation Test


From   Raphael Fraser <raphael.fraser@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Permutation Test
Date   Thu, 17 Nov 2005 22:41:12 -0500

Dear All,

In the first permutation test below Stata reports P=0.045, while in
the second permutation test Stata reports  P=0.063. I am of the
opinion that the two permutation tests are equivalent. Can anyone
explain why the P-values are different?

clear
capture program drop diff //this drops any previous program called diff//
program diff, rclass  //this is the beginning of the program//
      summarize count if treated //here we generated the sum if treated//
      local sumt = r(sum)  //and store it//
      summarize count if treated == 0 //here is the sum if not treated//
      local sum0 = r(sum)  //and stored//
      return scalar diff = `sumt' - `sum0' //here we calculate the diff//
end
//now we input the data//
input count   treated
    121         1
    118         1
    110         1
     90         1
     95         0
     34         0
     22         0
     12         0
end
//here we tell it to use the program diff and then use it in -permute-//

diff
set seed 12345
permute count diff=r(diff), reps(1000) nowarn nodots: diff

set seed 12345
permute count "diff" diff=r(diff), reps(1000) nowarn

Raphael

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index