Date:         Sat, 31 Jul 1999 15:32:16 -0500
Reply-To:     Annette Towler <towleraj@RUF.RICE.EDU>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Annette Towler <towleraj@RUF.RICE.EDU>
Content-Type: text/plain; charset="us-ascii"

Hello

I am having some problems calculating intraclass correlations for a data
set. I have calculated reliability (ICC(1, K) using Shrout and Fleiss'
equation, but cannot reconcile my figures with some previous calculations
on level of agreement. I am using S & F's ICC (1,1) equation to calculate
agreement i.e. BMS - WMS/BMS + (k-1)WMS.

Here is my ANOVA TABLE:

                                  Sum of         Mean
Source                  DF       Squares       Square  F Value
Model                  116     567.68212      4.89381     6.36

Error                 6273    4830.21550      0.77000

Corrected Total       6389    5397.89762

here are my calculations:

4.89 - 0.77/4.89 + (116)0.77 = .04

Another student obtained a level of agreement of .09 on this data set, so
one of us is wrong! Can someone point me in the right direction?

Thanks in advance.
Annette Towler
Doctoral Candidate
Psychology Department
Rice University
466 Sewall Hall, MS 25
6100 Main
Houston, Texas  77005-1892