residualEGA: Residualized 'EGA' In EGAnet: Exploratory Graph Analysis - A Framework for Estimating the Number of Dimensions in Multivariate Data Using Network Psychometrics

Description

`residualEGA` Estimates the number of dimensions after controlling for wording effects. EGA is applied in the residual of a random intercept item factor model (RIIFA) with one method factor and one substantive factor.

Usage

 `1` ```residualEGA(data, manifests, lat, negative.items, plot = TRUE) ```

Arguments

 `data` Matrix or data frame. Includes the variables to be used in the `residualEGA` analysis `manifests` Character vector. Vector indicating the names of the variables (items) to be used in the analysis. `lat` Numeric integer. Number of latent factors to be estimated. Only one substantive latent factor is recommended in the current version of the function. `negative.items` Numeric vector A numeric vector indicating the column of the negative items. `plot` Boolean. If `TRUE`, returns a plot of the residualized network and its estimated dimensions. Defaults to `TRUE`

Value

Returns a list containing:

 `openMx.model` OpenMX model `openMx.result` OpenMX results `openMx.std.par` OpenMX standardized parameters `ResidualMatrix` Residual matrix `EGA.Residuals` Results of the residualized EGA `Fit` Fit metrics of the network structure, calculated using the ggmfit function of the `qgraph` package `WordLoads` Loadings of the wording effects

Author(s)

Hudson F. Golino <hfg9s at virginia.edu> and Robert Moulder <rgm4fd@virginia.edu>

`EGA` to estimate the number of dimensions of an instrument using EGA and `CFA` to verify the fit of the structure suggested by EGA using confirmatory factor analysis.
 ``` 1 2 3 4 5 6 7 8 9 10 11``` ```data <- optimism ## Not run: # resEGA example opt.res <- residualEGA(data = data, manifests = colnames(optimism), lat = 1, negative.items = c(3,7,9), plot = TRUE) # Fit: opt.res\$Fit ## End(Not run) ```