|Date: ||Sat, 23 May 1998 17:44:55 +0200|
|Reply-To: ||Pentti Andersson <pentti@ALGONET.SE>|
|Sender: ||"SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>|
|From: ||Pentti Andersson <pentti@ALGONET.SE>|
|Subject: ||Calculate Kappa|
Two of my questionnaires has been answered by a group of 109 respondents.
The questionnaires consists of 18 respectively 40 questions.
The first questionnaire has 7 answering alternatives
(1=I agree completely <--> 4=Uncertain <--> 7=I disagree completely)
and the other has 5 alternatives
(1=Not characteristic at all for me <-3=uncertain->5=Very characteristic for
Some of the questions within the questionnaires measures the same thing and
are supposed to be grouped to one new aggregate. Some of the questions also
correspond between the two questionnaires.
The intention calculating Kappa is to get out a concurrent validity between
The first problem is how to do the appropriate transformations. The second
is how to do the final calculation.
Do you know how to calculate Kappa under these circumstances ?