Dear Statalist,
I have a very rudimentary understanding of what I am trying to do, so I
hope you will bear with me.
I need to do one-sided testing in a multinomial setting with exact (i.e.,
non-asymptotic) inference comparing mean outcomes for randomized treatment
(n=58) and control (n=65) groups. Thus I want to test a vector null of
mu_t > mu_c against the alternative mu_t=mu_c.
I have no idea what this procedure would be called, and if anyone can
recommend a source and/or a module in Stata to do this, I would be most
grateful.
My data looks like this.
n treatment outcome1 ... outcomek
1 1 1 ... 1
. 0 2 ... 2
. . . ... .
. . . ... .
. . . ... .
123 1 100 ... 1
Dimitriy Masterov
_______________________________________________________________________________
Dimitriy V. Masterov
Work:
Center for Social Program Evaluation
1155 East 60th St. Room 038
Chicago, IL 60637
Work: (773)256-6005
Fax: (773)256-6313
*
* 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/
