KappaU < CTSpedia

Kappa.u

This R function is to calculate kappa statistics based on U- statistics.

It compares two raters' ratings within a longitudinal data setting.

Reference:

Ma Y, Tang W, Feng C, and Tu X.M. "Inference for Kappas for Longitudinal

Study Data: Applications to Sexual Health Research" Biometrics 2008 64: 781-789.

Parameters:

The required parameters (n, g, t, x, y, weight):

1. n=Number of subjects
2. g=Number of categories
3. t= Number of time points
4. x =Matrix for the first rater's ratings, where element x(i,j) represents the rater's rating on the ith subject at time j
5. y =Matrix for the second rater's ratings, where element y(i,j) represents the rater's rating on the ith subject at time j
6. Weight=Indicator of weight. Where weight=1 for unweighted kappa; weith= 2 for Cicchetti-Allison weighted kappa; weight=3 for Fleiss-Cohen weighted kappa.

Programmer: Dr. Yan Ma

Revision: December 20, 2010

Disclaimer: This R function is developed by Dr. Yan Ma from Weill Cornell Medical College , along with other members in the Department of Biostatistics and Computational Biology at the University of Rochester under the auspice of the CTSI BERD with the intent to facilitate data analyses and reporting in clinical and related research. It is copyrighted by Dr. Yan Ma on December 20, 2010 and distributed for free public access.

Examples(s) Example: an example to execute the kappa.u function.

kappa.u output.txt: the output file produced by the example program.

kappa.u.txt: This R function is to calculate kappa statistics based on U- statistics

Topic attachments
I	Attachment	Action	Size	Date	Who	Comment
txt	kappa.u.txt	manage	9 K	21 Dec 2010 - 15:57	UnknownUser	This R function is to calculate kappa statistics based on U- statistics