What is it about?
Describes the R package kaphom, which is developed in order to easily perform four different homogeneity tests recommended to be used to test the homogeneity of intra-class kappa statistics, from multiple independent studies or a single stratified study. R package kaphom, contains Fleiss, Donner Goodness of Fit, Likelihood Score and Modified Score homogeneity tests. The theoretical background of the homogeneity test statistics are given and the developed algorithm is explained in the content. Also, included functions and practical examples on real data are given.
Photo by Markus Spiske on Unsplash
Why is it important?
Because the implementation includes four different tests each performing better in terms of type I error and power under different conditions such as sample size and number of kappa statistics, it is very useful in that it allows the user to choose the most suitable test option. In addition, this package can be used in theory to perform the homogeneity test of the kappa statistic at the desired number since there is no limit in terms of the number of strata or study.
Read the Original
This page is a summary of: kaphom: An R package for testing the homogeneity of intra-class kappa statistics, Communications in Statistics - Simulation and Computation, January 2019, Taylor & Francis, DOI: 10.1080/03610918.2018.1538457.
You can read the full text:
The following have contributed to this page