WGA: WGA: Within-Group Agreement

In james-lebreton/WGA: WGA: Within-Group Agreement & Data Aggregation

WGA: Within-Group Agreement

Description

This function computes multiple estimates of withing-group agreement including: James, Demaree, & Wolf's (1984) RWG(J), Burke, Finkelstein, & Dusig's (1999) AD(J), and Brown & Hauenstein's (2005) AWG(J). Estimates of RWG(J) are computed for multiple null distributions.

Usage

WGA(x, grpid, scale, model, reset = F, cutoff = 0.5)

Arguments

x	A vector representing a single item or a matrix representing a scale of interest. If a matrix, each column of the matrix represents a scale item, and each row represents an individual respondent.
grpid	A vector identifying the groups from which x originated.
scale	A vector with the lower and upper response options (e.g., c(1,5)) for a five-point scale from strongly disagree to strongly agree.
model	User-supplied description of multilevel measurement model (e.g., consensus)
reset	Logical option for handling negative estimates of RWG; FALSE retains negative values; TRUE resets values to 0
cutoff	User-supplied cutoff value for justifying data aggregation

Details

The input consists of a data frame, the names of the grouping variable, and the names of items. The output consists of a data frame containing the group names, group sample sizes, the variance within each group, and the various estimates of agreement.

Value

Estimates of within-group agreement

Examples

data(lq2002, package = "multilevel")
WGA(x=lq2002[,3], grpid = lq2002$COMPID, scale=c(1,5), model = "consensus", reset = FALSE)

james-lebreton/WGA documentation built on Oct. 17, 2022, 4:05 a.m.