Here are some sources on computing confidence intervals for
kappa:
(1) From the www.spssstools.net website: Dave Nichols
wrote a macro back in the 1990s for the standard error and
confidence interval of kappa. The SPSS code here builds
upon Dave's work; see:
http://www.spsstools.net/Syntax/Matrix/CohensKappa.txt(2) A website that goes over basic concepts for kappa
as well as the Koch and Landis criteria for evaluating kappa
(which may or may not be relevant);see:
http://www-users.york.ac.uk/~mb55/msc/clinimet/week4/kappa.htm(3) From books.google.com, a section from a nonparametrics
statistics text on kappa:
http://books.google.com/books?id=M59rMlCM4FIC&pg=PA268&lpg=PA268&dq=spss+%22confidence+interval+for+kappa%22&source=bl&ots=1Ah5La8eJg&sig=_jSdwX7C7juoutVzxdmKzmGTtT4&hl=en&ei=7OTeTLP5NM6s8AasoN3aCA&sa=X&oi=book_result&ct=result&resnum=1&ved=0CBMQ6AEwAA#v=onepage&q=spss%20%22confidence%20interval%20for%20kappa%22&f=false(if the above link break, search books.google.com for
"confidence interval for kappa".
-Mike Palij
New York University
[hidden email]
----- Original Message -----
From: J McClure <
[hidden email]>
Date: Saturday, November 13, 2010 12:44 pm
Subject: confidence intervals for kappa?
To:
[hidden email]
> Hi,
> Is there a way to calculate confidence intervals for a kappa statistic.
> If I bought the bootstrap module would I be able to do this?
> Thanks,
> Jan
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
>
[hidden email] (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
