kappa_test {kappaGold} | R Documentation |
Significance test for homogeneity of kappa coefficients
Description
When groups of different subjects are rated on a nominal scale. Assuming independence of subjects and their ratings between groups a chi-squared test for equality of kappa between these groups is performed. The test requires estimates of kappa and its standard error per group.
Usage
kappa_test(kappas, val = "value0", se = "se0", conf.level = 0.95)
Arguments
kappas |
list of kappas from different groups. It uses the kappa estimate and its standard error. |
val |
character. Name of field to extract kappa coefficient estimate. |
se |
character. Name of field to extract standard error of kappa. |
conf.level |
numeric. confidence level of confidence interval for overall kappa |
Details
A common overall kappa coefficient across groups is estimated. The test statistic assesses the weighted squared deviance of the individual kappas from the overall kappa estimate. The weights depend on the provided standard errors.
Value
list containing the test results, including the entries statistic
and p.value
(class htest
)
References
Joseph L. Fleiss, Statistical Methods for Rates and Proportions, 3rd ed., 2003, section 18.1
Examples
# script concordance test on 34 clinical situations,
# rated by 39 students and 11 experts
kappa_stud <- kappam_fleiss(SC_test[, 1:39])
kappa_expert <- kappam_fleiss(SC_test[, 40:50])
# compare student and expert agreement
kappa_test(kappas = list(kappa_stud, kappa_expert))