delta.pair: Compare dependent pairwise kappas (delta method)

In svanbelle/multiagree: Comparaison of dependent kappa coefficients

Compare dependent pairwise kappas (delta method)

Description

This function performs Hotelling's T square test using a variance-covariance matrix based on the delta method to compare dependent pairwise kappa coefficients

Usage

delta.pair(data, cluster_id, weight, multilevel = T, a.level = 0.05)

Arguments

data	a N x R matrix representing the classification of the N items by the R observers. The kappa coefficients are computed pairwise between column (1,2), (3,4), etc....
cluster_id	a vector of lenght N with the identification number of the K clusters
weight	the weighting scheme to be used in the computation of the kappa coefficients: 'unweighted' for Cohen's kappa, 'equal' for linear weights and 'squared' for quadratic weights
multilevel	a binary indicator equal to TRUE in the presence of multilevel data and FALSE otherwise
a.level	the significance level

Details

This function compare several dependent kappa coefficients obtained between pairs of observers. It uses Hotelling's T square test with the variance-covariance matrix obtained by the delta method. If only a single kappa coefficient is computed, the kappa coefficient and its standard error are returned.

Value

$kappa a G x 2 matrix with the G kappa coefficients to be compared in the first column and their corresponding standard error in the second column

$T_test a vector of length 2 with the value of Hotelling's T square test as first element and the p-value as second element

$confidence confidence intervals for the pairwise comparisons of kappa coefficients

$var the G x G correlation matrix of the kappa coefficients

Author(s)

Sophie Vanbelle [e-mail]

References

Vanbelle S. and Albert A. (2008). A bootstrap method for comparing correlated kappa coefficients. Journal of Statistical Computation and Simulation, 1009-1015

Vanbelle S. (in press). Comparing dependent agreement coefficients obtained on multilevel data. Biometrical journal. doi: 10.1002/bimj.201600093

Vanbelle S. (2014). A New Interpretation of the Weighted Kappa Coefficients. Psychometrika. Advance online publication. doi: 10.1007/s11336-014-9439-4

Examples

 
#dataset (not multilevel) (Vanbelle and Albert, 2008)

data(depression)
attach(depression)
delta.pair(data=cbind(diag,BDI,diag,GHQ),cluster_id=ID,weight='unweighted',multilevel=FALSE)

#dataset (multilevel) (Vanbelle, xxx)

data(FEES)
attach(FEES)
dat<-cbind(val_CO,val_COR,val_MH,val_MHR,val_TB,val_TBR) #formating the data matrix
delta.pair(data=dat,cluster_id=subject,weight='equal')

svanbelle/multiagree documentation built on Feb. 9, 2023, 2:37 p.m.