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

st: RE: using stci with weighted data; and multiple test procedure


From   "Jann, Ben" <ben.jann@soz.gess.ethz.ch>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: using stci with weighted data; and multiple test procedure
Date   Wed, 3 Mar 2004 10:17:09 +0100

Douglas asked:
> ...
> Seondly, I have several treatment groups.  To evaluate the 
> significance 
> of the differences in lifespans between the groups I performed a 
> logrank test.  Now I would like to perform a series of pairwise 
> comparisons between the groups.  What is the appropriate procedure to 
> protect against multiple comparisons (is there something like 
> Bonferroni or Scheffe that should follow the logrank)?

Maybe -_mtest- will give you what you want. Assume X1, X2, X3, ... are
the variables identifying the pairs of groups, then type something like:

foreach X of var X1 X2 X3 ... {
 sts test `X'
 matrix pvalues=nullmat(pvalues)\ 1-chi2(`r(df)',`r(chi2)')
}
_mtest adjust pvalues, mtest(bonferroni)
matrix list r(result)
matrix drop pvalues

(the unadjusted p-values of the single tests are saved to the matrix
"pvalues"; the matrix "r(result)" contains the bonferroni-ajusted
p-values)

ben

*
*   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