Fliess' Kappa

[Lindsay1011]

I am using SPSS 16 for Mac and I am trying to calculate Fliess' Kappa. What is the best way to do this and how is best to set up your data?

Thanks!
Lindsay

[Bruce Weaver]

Lindsay1011 wrote

I am using SPSS 16 for Mac and I am trying to calculate Fliess' Kappa. What is the best way to do this and how is best to set up your data?

Thanks!
Lindsay

Do you mean you want to compute a multi-rater kappa? If so, this thread from the comp.soft-sys.stat.spss newsgroup may be helpful.

http://groups.google.ca/group/comp.soft-sys.stat.spss/browse_thread/thread/abe40198c7b640a7/cba870b83c559ec7?hl=en&#cba870b83c559ec7

[Lindsay1011]

Yes-- I cannot run a normal ICC because I dont have enough variance in some of my variables so I am wanting to run Fleiss' Kappa (because I have multiple raters), so what you've sent sounds right-- thanks! However, I like the woman who emailed about that first, am not familiar enough with syntax to know exactly which of these bits I'm meant to change and which I am not. Do you have any way of highlighting the parts that need to be changed in the syntax? I'm sorry, I'm not quite sure what is meant by "you specify the variable names "when you call the macro"... sorry, I've just never used someone else's code when doing this before.

Thanks so much for your help,
Lindsay

[ANDRES ALBERTO BURGA LEON]

I don´t kinow how to do it in SPSS but you can use MacKappa software:

http://www.public.asu.edu/~mwwatkin/Watkins3.html

Andrés

Mg. Andrés Burga León
Coordinador de Análisis e Informática
Unidad de Medición de la Calidad Educativa
Ministerio de Educación del Perú
Calle El Comercio s/n (espalda del Museo de la Nación)
Lima 41
Perú
Teléfono 615-5840

Lindsay1011 <[hidden email]>
Enviado por: "SPSSX(r) Discussion" <[hidden email]>

09/08/2010 08:52 a.m.

Por favor, responda a
Lindsay1011 <[hidden email]>

Para	[hidden email]
cc
Asunto	Fliess' Kappa

I am using SPSS 16 for Mac and I am trying to calculate Fliess' Kappa. What
is the best way to do this and how is best to set up your data?

Thanks!
Lindsay
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Fliess-Kappa-tp2268098p2268098.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

[Bruce Weaver]

Lindsay1011 wrote

Yes-- I cannot run a normal ICC because I dont have enough variance in some of my variables so I am wanting to run Fleiss' Kappa (because I have multiple raters), so what you've sent sounds right-- thanks! However, I like the woman who emailed about that first, am not familiar enough with syntax to know exactly which of these bits I'm meant to change and which I am not. Do you have any way of highlighting the parts that need to be changed in the syntax? I'm sorry, I'm not quite sure what is meant by "you specify the variable names "when you call the macro"... sorry, I've just never used someone else's code when doing this before.

Thanks so much for your help,
Lindsay

If you can't compute an ICC, for some reason, I'd expect you to also have trouble computing a kappa--well, a weighted kappa at least.  But anyway, here's how to call Dave Nichol's macro.  Suppose you have 5 raters (variables RATER1 to RATER5).  Call the macro like this:

mkappasc vars= rater1 rater2 rater3 rater4 rater5 /.

HTH.