Date:         Mon, 27 Oct 2003 20:57:54 +0000
Reply-To:     Jeremy Miles <jnvm1@york.ac.uk>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Jeremy Miles <jnvm1@york.ac.uk>
Subject:      Re: Looking for name of crosstabs phenomenon
Comments: To: Martin Sherman <MSherman@loyola.edu>
In-Reply-To:  <sf9d3dab.072@GWMAIL01.LOYOLA.EDU>
Content-Type: text/plain; charset="us-ascii"; format=flowed

At 20:00 27/10/2003, Martin Sherman wrote:
>Dear list: I am looking for the name of a crosstabs phenomenon where a
>relation exists to a positive degree in two separate crosstabs but when
>combined into one crosstabs the relation changes direction (primarily
>because of how the cases are distributed). Thanks,

I believe you are after Simpson's paradox.

Here's a web site:

http://www.intuitor.com/statistics/SimpsonsParadox.html

JM
--
Jeremy Miles, Lecturer in Biostatistics,     Health Sciences (Area 4)
University of York, YO10 5DD                    mobile: 07941 228 018
mailto:jnvm1@york.ac.uk             http://www-users.york.ac.uk/~jnvm1
[working at home]