Light's kappa

[bflorian]

I am looking for a macro to compute Light's kappa. Thank you!

[David Marso]

Post a reference (one available to us non privileged peeps lacking University access to journals despite paying taxes to support research grants).
OR attach a pdf?
Maybe someone has already written one.  
What are you using it for?
If you aren't working for corporate america or the military (I also consider the police military)
Maybe I'll take it on?
--
--

bflorian wrote

I am looking for a macro to compute Light's kappa. Thank you!

[Bruce Weaver]

The "Instruction Manual" link here takes you to a word doc containing some relevant info.  Unfortunately, the links that look like they should yield syntax files yield 404s instead.

  http://www.ccitonline.org/jking/homepage/interrater.html

David Marso wrote

Post a reference (one available to us non privileged peeps lacking University access to journals despite paying taxes to support research grants).
OR attach a pdf?
Maybe someone has already written one.  
What are you using it for?
If you aren't working for corporate america or the military (I also consider the police military)
Maybe I'll take it on?
--
--

bflorian wrote

I am looking for a macro to compute Light's kappa. Thank you!

[bflorian]

I have 18 raters that scored twice a total number of 44 ultrasound images using a Likert scale (0-3). I have to compute intra-rater and inter-rater reliability. Initaially I used ICC for both but the reviewers recommended to use Cohen's k for intra-rater and Light's k for inter-rater computations.

 

[Bruce Weaver]

If the reviewers are asking for Cohen's weighted kappa (with quadratic weights), then this old thread is relevant.

http://spssx-discussion.1045642.n5.nabble.com/Kappa-for-more-than-2-raters-tp1085432p1085433.html

bflorian wrote

I have 18 raters that scored twice a total number of 44 ultrasound images using a Likert scale (0-3). I have to compute intra-rater and inter-rater reliability. Initaially I used ICC for both but the reviewers recommended to use Cohen's k for intra-rater and Light's k for inter-rater computations.

[David Marso]

A simple Google "Light's Kappa"
http://www.search.ask.com/web?l=dis&o=15555&qsrc=2873&q=Light%27s%20Kappa
Some ways down:
http://www.ccitonline.org/jking/homepage/Instructions.doc
Reading through this Light's Kappa looks fairly elementary.
Looks like our very own Brian D. was involved in the creation.
Maybe if you do a little bit of research you can find him.
Ask nicely and he might even send you a copy (or even better upload it here).
-------

bflorian wrote

I have 18 raters that scored twice a total number of 44 ultrasound images using a Likert scale (0-3). I have to compute intra-rater and inter-rater reliability. Initaially I used ICC for both but the reviewers recommended to use Cohen's k for intra-rater and Light's k for inter-rater computations.

[bflorian]

Most of these links end in 404 :(

[David Marso]

I found that too.  
EXCEPT look at the Instructions.doc link I posted.
Formula for Light's Kappa is there.
Looks like a fairly straightforward computation.
Who is listed as author? Brian Dates.
He is active here on the SPSSX-L.
Follow the bread crumbs and contact Brian.
Ask nicely and he will more than likely send you a copy.
I have a copy but will not post it without his permission (that's just how I roll).
-------------------------------------------------------------------

bflorian wrote

Most of these links end in 404 :(

[Ware, William B]

There is a function in the R irr package... kappam.light ( )   Also a function lkappa( ) is the psy package.

Bill

William B. Ware, Ph.D.
McMichael Professor of Education 2011-2013
Educational Psychology, Measurement, and Evaluation
CB #3500 - 118 Peabody Hall
University of North Carolina at Chapel Hill
Chapel Hill, NC     27599-3500
Office: (919)-962-0132  (Office Assistant:  Sharon Powell)
Fax:      [phone]
Office:  118 Peabody Hall
EMAIL: [hidden email] <mailto:[hidden email]>
Adjunct Professor, School of Social Work
Academy of Distinguished Teaching Scholars at UNC-Chapel Hill



-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of David Marso
Sent: Sunday, March 24, 2013 10:23 AM
To: [hidden email]
Subject: Re: Light's kappa

I found that too.
EXCEPT look at the *Instructions.doc* link I posted.
Formula for Light's Kappa is there.
Looks like a fairly straightforward computation.
Who is listed as author? *Brian Dates*.
He is active here on the SPSSX-L.
Follow the bread crumbs and contact Brian.
Ask nicely and he will more than likely send you a copy.
I have a copy but will not post it without his permission (that's just how I roll).
-------------------------------------------------------------------

bflorian wrote
> Most of these links end in 404 :(





-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Light-s-kappa-tp5719021p5719044.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
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

[bdates]

Good morning, all.  Here's the syntax for Light's kappa.  It's one of two expansions of Cohen's kappa for multiple raters, and averages all the two-rater kappas.  The other expansion is Hubert's kappa also known as Conger's kappa, Davies and Fleiss' kappa, and Berry and Mielke's kappa, each differentiated by uinque standard error terms.  Hubert's kappa averages all the two-rater Pe terms, and then uses the overall Pa. I have that too, if anyone is interested.

Brian


Light's_Kappa.sps