|Date: ||Tue, 6 May 1997 08:54:08 +0100|
|Reply-To: ||Jeremy Miles <J.N.V.Miles@DERBY.AC.UK>|
|Sender: ||"SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>|
|From: ||Jeremy Miles <J.N.V.Miles@DERBY.AC.UK>|
|Subject: ||Re: heywood cases|
|Content-Type: ||text/plain; charset="us-ascii"|
At 08:37 28/04/97 -0700, Michelle Yik wrote:
>How are heywood cases defined? My understanding is that heywood cases
>are noted when the TDs are negative and the corresponding LXs are
>greater than one. Are there any other cases included in this set? What
>about TDs greater than 1? TDs greater than 1 and negative?
A Heywood case occurs when a statistical estimation procedure estimates a
negative variance. As a variance cannot be less than 0 (mathematically
because it is a sum of squares, and conceptually because something cannot
have less than no variation).
>What are the major references for them?
Jeremy Miles, AVRU, Derby University, DE3 5GX Fax: 01332 622287
Tel: 01332 622222 x. 2146 firstname.lastname@example.org
======================No Space for a Joke======================