Date:         Mon, 14 Jul 1997 07:44:51 GMT
Reply-To:     Adrian Esterman <esterman.adrian@HEALTH.SA.GOV.AU>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From:         Adrian Esterman <esterman.adrian@HEALTH.SA.GOV.AU>
Organization: EDS Australia
Subject:      Re: intercoder reliability test

(1) Create a file with cases as the coders and and variables as the items
then perform Kendal's test for concordance under non-parametric stats
k-related samples.
 
(2) Transpose the data set so that coders are now the variables and items
the cases (use FLIP in old versions, or transpose in SPSS 7.5), then use
RELIABILITY. The Cronbach's alpha provided is the inter-rater reliability
coefficient
 
Adrian Esterman