RE: Calculating Cohen's Simple Kappa in PSPP

[MACDOUGALL Margaret]

Dear John

I did not assume that there was an error in the dataset or syntax, as my 
colleague is relying on the PSPP User Manual and the procedure is very simple. 
However, I had assumed that other users might have experienced similar issues 
and that rather, the problem was with PSPP.  Is this not a possibility?

Best wishes

Margaret



-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.


-----Original Message-----
From: John Darrington [mailto:address@hidden 
Sent: 25 June 2015 06:10
To: MACDOUGALL Margaret
Cc: address@hidden
Subject: Re: Calculating Cohen's Simple Kappa in PSPP

Could you perhaps post the dataset and the syntax you used, which provokes this 
problem?

J'

On Wed, Jun 24, 2015 at 07:59:33PM +0000, MACDOUGALL Margaret wrote:
     
     Hello
     
     I would value advice on output which was sent to me from calculating 
Cohen's simple Kappa using PSPP. The output demonstrates the following:
     
     
     a)      a discrepancy between the standard errors calculated by  PSPP and 
SPSS (0.07 versus 0.088, respectively)
     
     and
     
     b)      an empty cell under the label 'Approx sig.' in PSPP by contrast 
with the occurrence of the value '.000' in the corresponding cell for SPSS.
     
     Can anyone explain any of these anomalies, please?
     
     Best wishes
     

--
PGP Public key ID: 1024D/2DE827B3
fingerprint = 8797 A26D 0854 2EAB 0285  A290 8A67 719C 2DE8 27B3 See 
http://sks-keyservers.net or any PGP keyserver for public key.