tidySEM (version 0.2.8)

get_edges: Extract edges from a SEM model object

Description

Attempts to extract edges from a SEM model object, where edges are defined as regression paths and covariances between variables (nodes).

Usage

get_edges(x, label = "est_sig", ...)

Value

An object of class 'tidy_edges'

Arguments

x

A model object of class mplusObject or lavaan.

label

Either a character, indicating which column to use for edge labels, or an expression. See Details. Defaults to "est_sig", which labels edges with the estimated value with significance asterisks, as obtained from table_results. See Details and examples for more information.

...

Additional parameters passed to table_results. For example, users can pass the digits argument to control the number of digits in the edge label, or pass the columns argument to retain auxiliary columns in the tidy_edges data.frame for further processing (see Examples).

Details

The function get_edges identifies all regression paths, latent variable definitions, and covariances in the model as edges. The output of table_results for those paths is used to label the edges.

Custom labels

One way to create custom edge labels is by passing an expression to label. When an expression is passed to label, it is evaluated in the context of a data.frame containing the results of a call to table_results on the x argument.

Another way to create custom labels is by requesting auxiliary variables using the columns argument (which is passed to table_results), and then using these columns to construct a new label. See examples.

Examples

# Standard use
library(lavaan)
res <- sem("dist ~ speed", cars)
get_edges(res)

# Pass an expression to the 'label' argument for custom labels
get_edges(res, label = paste(est_sig, confint))

# Pass the argument 'columns' to table_results through '...' to retain
# auxiliary columns for further processing
edg <- get_edges(res, columns = c("est_sig", "confint"))
edg
edg <- within(edg, {label <- paste(est_sig, confint)})
edg