|Date: ||Thu, 13 May 2004 08:18:07 -0400|
|Sender: ||"SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>|
|From: ||Art Kendall <Arthur.Kendall@verizon.net>|
|Organization: ||Social Research Consultants|
|Subject: ||Re: Only 30 responses for T-test?|
|Content-Type: ||text/plain; charset=ISO-8859-1; format=flowed|
It seems that someone was pulling your leg.
Social Research Consultants
University Park, MD USA
Elsa-Sofia Morote wrote:
> Dear colleagues,
> I heard in a discussion that SPSS has some deficiences when applying
> and T-test to large samples. The person said "when you compare two
> and you have lets say 100 individuals in one group and 120 in the
> other, you
> have to take a randon sample of 30 to run a T-test, because SSPSS has
> deficiences"..."you must only have 27-30 responses for run T-test and
> in SPSS to overcome SPSS deficiences in samples...."
> Could somebody tell me if this is correct? Which deficiences SPSS has in
> F-test, and T-test? Why we have to take randon sample of our sample?
> Why we
> can only test with 27-30 responses? Any thoughts?
> Getting married? Find tips, tools and the latest trends at MSN Life