|Date: ||Thu, 6 Feb 1997 09:39:43 +0100|
|Reply-To: ||Hans-Peter Piepho <piepho@WIZ.UNI-KASSEL.DE>|
|Sender: ||"SAS(r) Discussion" <SAS-L@UGA.CC.UGA.EDU>|
|From: ||Hans-Peter Piepho <piepho@WIZ.UNI-KASSEL.DE>|
|Subject: ||Re: Negative intraclass correlations?|
|Content-Type: ||text/plain; charset="us-ascii"|
> I'm trying to estimate the degree of agreement between mothers and
>fathers in 172 families which I would like to use in further analyses.
>Both parents responded to 14 items using a 4-point Likert response
>scale. I'm using an intraclass correlation (ICC) (as opposed to a
>Pearson correlation) to measure the agreement across the 14 items for
>each set of parents. I've downloaded the SAS macro developed by Robert
>Hamer that implements the 6 types of ICCs identified by Shrout and
>Fleiss in their Psychological Bulletin article. The SAS macro uses Proc
>Glm to derive the variance components used to compute the particular
>About 15 of the 172 ICCs are negative which I would like to understand
>better since it doesn't seem possible to have a negative variance. In
>fact, one of the negative ICCs is a value over 1 (-1.42).
>Unfortunately, I can't find my copy of the Shrout and Fleiss article at
>the moment to see if they discuss this possibly. I would appreciate any
>ideas on how to deal with the negative ICCs or references to examine.
>firstname.lastname@example.org or email@example.com
I don't know about the macro, but I would guess the variance components are
estimated by the ANOVA method/methods of momets. It is quite possible to get
negative estimates by these methods. This is indication that the variance
is, in fact zero or very small, and/or that the sample size is small, so you
get a large standard error of your estimate.
Institut f. Nutzpflanzenkunde WWW: http://www.wiz.uni-kassel.de/fts/
Universitaet Kassel Mail: firstname.lastname@example.org
Steinstrasse 19 Fax: +49 5542 98 1230
37213 Witzenhausen, Germany Phone: +49 5542 98 1248