Tests of Matrix Structure for Construct Validation
Sub-routine to create Delta matrix
Convert character string in lavaan syntax into a list of indices
Permutation p-values for Gamma and t-statistics
Compute Gamma and t-statistics for a single permutation
Sub-routine to create Delta matrix for block-specific tests
Prepare data for box plots
Print results from matrixStrucTest
Sub-routine to compute OLS estimates of covariance between correlation...
Sub-routine to get covariance of z-transformed variables
Goodness-of-fit chi-squared statistic described by Steiger (1980).
Tests for block-diagonal structure in symmetric matrices (e.g. correlation matrices) under the null hypothesis of exchangeable off-diagonal elements. As described in Segal et al. (2019), these tests can be useful for construct validation either by themselves or as a complement to confirmatory factor analysis. Monte Carlo methods are used to approximate the permutation p-value with Hubert's Gamma (Hubert, 1976) and a t-statistic. This package also implements the chi-squared statistic described by Steiger (1980). Please see Segal, et al. (2019) <doi:10.1007/s11336-018-9647-4> for more information.