Carlo wrote:
after performing the following ttest, I would like to know about a possible
way to obtain with Stata 9.2/SE the one-way 95 CI for Ha: diff < 0.
ttest qaly, by(treat) unequal
Two-sample t test with unequal variances
----------------------------------------------------------------------------
Group Obs Mean Std. Err. Std. Dev. [95% Conf. Interval]
0 250 1.1472 .0158906 .2512527 1.115903
1.178497
1 250 1.1872 .0157876 .249624 1.156106 1.218294
----------------------------------------------------------------------------
Combined 500 -.0399999 .0224 -.0840101 .0040102
----------------------------------------------------------------------------
diff = mean(0) - mean(1) t = -1.7857
Ho: diff = 0 Satterthwaite's degrees of freedom =497.979
Ha: diff < 0 Ha: diff != 0 Ha: diff > 0
Pr(T < t) = 0.0374 Pr(|T| > |t|) = 0.0748 Pr(T > t) =0.9626
===========================================================
I am not sure that a "one-way CI" has any reasonable interpretation. But
you might get what you aim at by a 90% confidence interval. Rothman and
Greenland prefer 90% CIs - at least they did; I don't have their 3rd
edition here (see http://www.stata.com/bookstore/me.html) - probably
from similar reasons as yours.
ttest qaly, by(treat) unequal level(90)
Hope this helps
Svend
________________________________________________________
Svend Juul
Institut for Folkesundhed, Afdeling for Epidemiologi
(Institute of Public Health, Department of Epidemiology)
Vennelyst Boulevard 6
DK-8000 Aarhus C, Denmark
Phone, work: +45 8942 6090
Phone, home: +45 8693 7796
Fax: +45 8613 1580
E-mail: [email protected]
_________________________________________________________
*
* 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/
