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

Re: st: about Two independent samples t-test


From   Joseph Coveney <jcoveney@bigplanet.com>
To   Statalist <statalist@hsphsun2.harvard.edu>
Subject   Re: st: about Two independent samples t-test
Date   Sun, 21 Dec 2003 18:46:39 +0900

rghuang wrote (excerpted):

-------------------------------------------------------------------------------

. . . should we use ttest when we don't know if the variances is equal?

so whether should we use sdtest to find if the variances is equal?if not 
equal,should should i do if i want to see whether the mean for write is the 
same for males and females?

--------------------------------------------------------------------------------

-ttest- has two options for when the variances are not assumed to be equal:  
Satterthwaite adjustment of the degrees of freedom (-ttest , unequal-) and 
Welch adjustment of the degrees of freedom (-ttest , unequal welch-).  

I believe that it is not widely recommended to test for equality of variances 
before applying Student's t test.  If the ratio of variances is disturbing, 
then you can either apply the Satterthwaite or Welch approximation, or consider 
using a permutation t-test (-findit permt2-).

Joseph Coveney


*
*   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