|Date: ||Mon, 3 Aug 2009 16:32:07 -0700|
|Sender: ||"SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>|
|From: ||J M <jasonm@UCLA.EDU>|
|Subject: ||Re: Question on Comparing Two Averages|
|Content-Type: ||text/plain; charset=ISO-8859-1; DelSp="Yes"; format="flowed"|
If my data permitted it I would want to do a dependent t-test, correct?
Quoting Peter Flom <email@example.com>:
> J M <jasonm@UCLA.EDU> wrote
>>> HOWEVER, with n = 4,500, a tiny difference will be statistically
>>> significant. Will it be of any importance?
>> So, if I have 20% respond "yes" in 2008 and then 22% respond "yes" in
>> 2009 I can say that due to the large sample the difference would most
>> likely be statistically significant if we had the correct data to
>> actually test this claim?
> You can do an independent sample t-test of proportions, ignoring the
> matching. This is easy enough
> to do by hand, with the formula for a t-test.
> Or you can do a chi-square test:
> data today;
> input year $ yesno $ count;
> 2009 yes 990
> 2009 no 3510
> 2008 yes 900
> 2008 no 3600
> proc freq data = today;
> table year*yesno/chisq;
> weight count;
> Peter L. Flom, PhD
> Statistical Consultant
> www DOT peterflomconsulting DOT com