Date:         Thu, 3 Oct 1996 12:06:28 EDT
Reply-To:     Haiyi Xie <Haiyi.Xie@DARTMOUTH.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@UGA.CC.UGA.EDU>
From:         Haiyi Xie <Haiyi.Xie@DARTMOUTH.EDU>
Subject:      Re: T-Test

I have done it in both SAS (as suggested by John Whittington) and in the
spreadsheet too.  It is alway helpful to know how other people do it and a
better way of doing things from others.
 
Many Thanks to John Whittington, Robert M. Hamer, Hans_peter and Jay Weedon.
 
Haiyi
 
 
--- You wrote:
Haiyi Xie <Haiyi.Xie@DARTMOUTH.EDU> writes:
 
>        I wanted to do a whole bunch of t-test for two independent means,  but
>I don't have RAW DATA.  Only thing I have is means for each group, standard
>deviations and N for each group.
>        I can write a formula to compute t scores, but it is too much work.  I
>am wondering if there is a setup in SAS to do t-test for the info. I have.
>        Thank you very much,
 
Yes, you can do it.
First, you need to generate observations from your means
and standard deviations so that you have two groups of
observations, with appropriate Ns, means, and standard
deviations.  This can be done with PROC IML, or you can
use the random number features available in the data step,
along with PROC Standard to construct these observations.
 
Then you can use PROC T-TEST to analyse them.
--
--(Signature)      Robert M. Hamer hamer@rci.rutgers.edu 908 235 4218
--- end of quoted material ---