itemStability {EGAnet}R Documentation

Item Stability Statistics from bootEGA

Description

Based on the bootEGA results, this function computes and plots the number of times an item (variable) is estimated in the same factor/dimension as originally estimated by EGA (item.replication). The output also contains each item's replication frequency (i.e., proportion of bootstraps that an item appeared in each dimension; item.dim.rep) as well as the average network loading for each item in each dimension (item.loadings).

Usage

itemStability(bootega.obj, IS.plot = TRUE, structure = NULL, ...)

Arguments

bootega.obj

A bootEGA object

IS.plot

Should the plot be produced for item.replication? If TRUE, then a plot for the item.replication output will be produced. Defaults to TRUE

structure

User specified dimensionality structure.

...

Additional arguments. Used for deprecated arguments from previous versions of itemStability

Value

Returns a list containing:

membership

A list containing:

  • empirical The empirical memberships from the empirical EGA result

  • unique The unique dimensions from the empirical EGA result

  • bootstrap The memberships from the replicate samples in the bootEGA results

item.stability

A list containing:

  • empirical.dimensions The proportion of times each item replicated within the empirical EGA defined dimension. This EGA result is defined using the input from bootEGA

  • all.dimensions The proportion of times each item replicated in each of the empirical EGA defined dimensions. This EGA result is defined using the input from bootEGA

plot

A plot of the number of times each item replicated within the empirical EGA defined dimension.

mean.loadings

Matrix of the average standardized network loading (computed using net.loads) for each item in each dimension

Author(s)

Hudson Golino <hfg9s at virginia.edu> and Alexander P. Christensen <alexpaulchristensen@gmail.com>

References

Christensen, A. P., & Golino, H. (2021). Estimating the stability of the number of factors via Bootstrap Exploratory Graph Analysis: A tutorial. Psych, 3(3), 479-500.

Christensen, A. P., Golino, H., & Silvia, P. J. (2020). A psychometric network perspective on the validity and validation of personality trait questionnaires. European Journal of Personality, 34(6), 1095-1108.

See Also

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.

Examples


# Load data
wmt <- wmt2[,7:24]

## Not run: # Estimate EGA network
## plot.type = "qqraph" used for CRAN checks
## plot.type = "GGally" is the default
ega.wmt <- EGA(data = wmt, model = "glasso", plot.type = "qgraph")

# Estimate dimension stability
boot.wmt <- bootEGA(data = wmt, iter = 100, typicalStructure = TRUE,
plot.typicalStructure = TRUE, model = "glasso", plot.type = "qgraph",
type = "parametric", ncores = 2)

## End(Not run)

# Estimate item stability statistics
res <- itemStability(boot.wmt)

# Changing plot features (ggplot2)
## Changing colors (ignore warnings)
### qgraph Defaults
res$plot +
    ggplot2::scale_color_manual(values = rainbow(max(res$membership$unique)))

### Pastel
res$plot +
    ggplot2::scale_color_brewer(palette = "Pastel1")

## Changing Legend (ignore warnings)
res$plot +
    ggplot2::scale_color_discrete(labels = "Intelligence")


[Package EGAnet version 1.1.0 Index]