Hi Mary,
You can discuss the following book:
Categorical Data Analysis by Alan Agresti
two or three months back I went mad for finding the ordinal version of McNemar test or Stuart - Maxwell test. But i did not find anything. So I doubt whether ordinal version of McNemar test or Stuart - Maxwell test are discovered till date.
For the time being you can use Stuart Maxwell test for your ordinal data. We can apply tests which are actually for nominal data to the ordinal data and it is statistically valid. But the reverse we cannot do. However if we apply the nominal tests (tests which are mainly for nominal data) to the ordinal data it will reduces the power of test, which in turn increase type-II error. I suggest you to read the following link:
http://ourworld.compuserve.com/homepages/jsuebersax/mcnemar.htm
However best of luck to you
Thanks and Regards,
MADAN
Mary Swinson <[log in to unmask]> wrote:
Hi All,
I am looking for a generalization of Mcnemar's test to k*k tables (k>2). I came across the Stuart-Maxwell test in R (concord package) which seemed to do what I want but was unable to find any documentation/formula on it.
Also are there tests for k*k tables (k>2) for ordinal data?
For example I have 2 judges each grade a student's paper (A-E), giving a 5*5 table of ordinal counts where A is better than B,...E.
Any pointers/references most welcome.
regards,
Mary
---------------------------------
Yahoo! Messenger with Voice. Make PC-to-Phone Calls to the US (and 30+ countries) for 2¢/min or less.
--------------
Madan Gopal Kundu
Biostatistician and SAS Programmer
Ranbaxy R&D
Gurgaon, Haryana
India
Web: http://www.freewebs.com/madanstata
mobile: 91-9868788406
e-mail: [log in to unmask]
Click to join Statisticians_group
---------------------------------
Here's a new way to find what you're looking for - Yahoo! Answers
Send FREE SMS to your friend's mobile from Yahoo! Messenger Version 8. Get it NOW
|