Date:         Tue, 27 Sep 2005 13:03:45 +0200
Reply-To:     Marta García-Granero
              <biostatistics@terra.es>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Marta García-Granero
              <biostatistics@terra.es>
Organization: Asesoría Bioestadística
Subject:      Re: need help on 2 different samples
In-Reply-To:  <1d11d5730509262325227a245f@mail.gmail.com>
Content-Type: text/plain; charset=ISO-8859-1

Hi Roy,

If I understand you correctly, variable A has been measured in 60
people and variable B in 30 DIFFERENT people, so you have a total
sample size of 90 subjects (60 sample A + 30 sample B). Correct?

In that case, neither regression nor correlation analysis is possible,
because both methods require PAIRS of data: the same subjects for both
variables. There is no workaround solution for that, sorry.

RF> i have 2 variables from 2 different samples. e.g. var A collected from
RF> 60 respondents and var B collected from 30 different respondents.
RF> they're stored in 2 different files. is there any way to make a
RF> correlation or regression analysis between those variables? and if it
RF> can, will there be 30 missing values in the result?

--
Regards,
 Marta                            mailto:biostatistics@terra.es