TAM — WLErel" />
WLErel.Rd
Functions for computing reliability estimates.
WLErel(theta, error, w=rep(1, length(theta)), select=NULL) EAPrel(theta, error, w=rep(1, length(theta)), select=NULL)
theta | Vector with theta estimates |
---|---|
error | Vector with standard errors of theta estimates |
w | Optional vector of person weights |
select | Optional vector for selecting cases |
The reliability formulas follow Adams (2005). Let \(v\) denote
the variance of theta
estimates and let \(s\) denote
the average of the squared error
. Then, the WLE reliability is
defined as \(1-s/v=(v-s)/v\) while the EAP reliability is defined as
\(1 - s/(s+v)=v/(s+v)\).
Numeric value
Adams, R. J. (2005). Reliability as a measurement design effect. Studies in Educational Evaluation, 31(2), 162-172. doi: 10.1016/j.stueduc.2005.05.008
############################################################################# # EXAMPLE 1: Toy example for reliability functions ############################################################################# set.seed(9897) N <- 100 # simulate theta and error SDs x <- stats::rnorm(N,sd=2) error <- stats::runif(N, .7, 1.3) # compute WLE reliability WLErel(x,error) # compute EAP reliaility EAPrel(x,error)