pstrel

A character string indicating what estimate to plot from the strel output object

estimate

A number for the threshold to be tested against

low.bound

takes a mcmc posterior sample of any of the single test reliability estimates
and calculates any given probability of the estimate being bigger
or smaller than an arbitrary value

So far, it provides the most common single test reliability estimates, being:
Coefficient Alpha, Guttman's lambda-2/-4/-6, greatest lower bound and Mcdonald's Omega.
The Bayesian estimates are provided with credible intervals.
The method for the Bayesian estimates, except for omega, is sampling from the posterior inverse Wishart for the covariance matrix based measures.
See Murphy (2007) <https://www.seas.harvard.edu/courses/cs281/papers/murphy-2007.pdf>.
Gibbs Sampling from the joint conditional distributions of a single factor model in the case of omega.
See Lee (2007, ISBN:978-0-470-02424-9).
Methods for the glb are from Moltner and Revelle (2018) <https://www.rdocumentation.org/packages/psych/versions/1.8.10/topics/glb.algebraic>;
lambda-4 is from Benton (2015) <doi:10.1007/978-3-319-07503-7_19>;
the principal factor analysis is from Schlegel (2017) <https://www.r-bloggers.com/iterated-principal-factor-method-of-factor-analysis-with-r/>;
and the analytic alpha interval is from Bonnett and Wright (2014) <doi:10.1002/job.1960>.

pstrel: probability of estimate being bigger than threshold

Description

Usage

Arguments

Examples