identify_items_partial: Identify items for partial invariance

In brianmsm/antools: Functions and utilities for analysis in R

Identify items for partial invariance

Description

This function uses 2 lavaan functions to generate a table (in tibble format) to identify which items and specifications among the groups could be generating problematic situations.

Usage

identify_items_partial(fit, cutoff.value = 0.1, detailed = FALSE)

Arguments

fit	A lavaan object that is estimated by lavaan::cfa(), lavaan::sem() or semTools::measEq.syntax().
cutoff.value	By default, only p-values below 0.10 are retained. If you want to obtain all of them in their entirety, indicate the value as NULL.
detailed	Defaults to FALSE, and will display only the essential information requested. If you want the complete columns obtained with lavaan::parTable(), set to TRUE.

Value

A tibble::tibble() to identify items and specifications that, when indicated, could solve non-invariance problems.

See Also

lavaan::parTable(), lavaan::lavTestScore()

Examples

library(semTools)
HS.model <- ' visual  =~ x1 + x2 + x3
              textual =~ x4 + x5 + x6
              speed   =~ x7 + x8 + x9 '

fit_scalar <- measEq.syntax(configural.model = HS.model,
                            data = lavaan::HolzingerSwineford1939,
                            estimator = "MLR",
                            parameterization = "theta",
                            ID.fac = "std.lv",
                            ID.cat = "Wu.Estabrook.2016",
                            group = "sex",
                            group.equal = c("loadings", "intercepts"),
                            return.fit = TRUE)

identify_items_partial(fit_scalar)

brianmsm/antools documentation built on Feb. 13, 2023, 3:07 a.m.