semptools (version 0.3.2)

set_cfa_layout: Configure the layout of factors of a CFA graph by semPaths

Description

Configure the layout of factors and adjust other aspects of a CFA graph by semPaths.

Usage

set_cfa_layout(
  semPaths_plot,
  indicator_order = NULL,
  indicator_factor = NULL,
  fcov_curve = 0.4,
  loading_position = 0.5,
  point_to = "down"
)

Value

A qgraph::qgraph based on the original one, with various aspects of the model modified.

Arguments

semPaths_plot

A qgraph::qgraph object generated by semPaths, or a similar qgraph object modified by other semptools functions.

indicator_order

A string vector of the indicators. The order of the names is the order of the indicators in the graph, when they are drawn on the bottom of the graph. The indicators should be grouped by the factors on which they load on. For example, if x1, x2, x4 load on f2, and x3, x5, x6 load on f1, then vector should be either c("x1", "x2", "x4", "x3", "x5", "x6") or c("x3", "x5", "x6", "x1", "x2", "x4"). Indicators within a group can be ordered in any way. If it is a named vector, its names will be used for the argument indicator_factor. If it is NULL (default), auto_indicator_order() will be called to determine the indicator order automatically.

indicator_factor

A string vector of the same length of the indicator order, storing the name of the factor for which each of the indicator in indicator_factor loads on. For example, if x1, x2, x4 load on f2, and x3, x5, x6 load on f1, and indicator_order is c("x3", "x5", "x6", "x1", "x2", "x4"), then indicator_factor should be c("f2", "f2", "f2", "f1", "f1", "f1"). If NULL (default) and indicator_order is a named vector (supplied by users or generated by auto_indicator_order()), then it will be set to the names of indicator_order.

fcov_curve

A number used to set the curvature of the inter-factor covariances. Default is .4.

loading_position

The positions of all factor loadings. Default is .5, on the middle of the arrows. Larger the number, closer the loadings to the indicators. Smaller the number, closer the loadings to the factors.

point_to

Can be "down", "left", "up", or "right". Specify the direction that the factors "point" to the indicators. Default is "down".

Details

Modify a qgraph::qgraph object generated by semPaths based on a confirmatory factor analysis model.

Examples

library(lavaan)
library(semPlot)
mod <-
 'f1 =~ x01 + x02 + x03
  f2 =~ x04 + x05 + x06 + x07
  f3 =~ x08 + x09 + x10
  f4 =~ x11 + x12 + x13 + x14
 '
fit_cfa <- lavaan::sem(mod, cfa_example)
lavaan::parameterEstimates(fit_cfa)[, c("lhs", "op", "rhs", "est", "pvalue")]
p <- semPaths(fit_cfa, whatLabels="est",
       sizeMan = 2.5,
       nCharNodes = 0, nCharEdges = 0,
       edge.width = 0.8, node.width = 0.7,
       edge.label.cex = 0.6,
       style = "ram",
       mar = c(10,10,10,10))
indicator_order  <- c("x04", "x05", "x06", "x07", "x01", "x02", "x03", "x11",
                      "x12", "x13", "x14", "x08", "x09", "x10")
indicator_factor <- c( "f2",  "f2",  "f2",  "f2",  "f1",  "f1",  "f1",  "f4",
                      "f4",  "f4",  "f4",  "f3",  "f3",  "f3")
p2 <- set_cfa_layout(p, indicator_order,
                         indicator_factor,
                         fcov_curve = 1.5,
                         loading_position = .8)
plot(p2)

# Use a named vector for indicator_order
indicator_order2 <- c(f2 = "x04", f2 = "x05", f2 = "x06", f2 = "x07",
                     f1 = "x01", f1 = "x02", f1 = "x03",
                     f4 = "x11", f4 = "x12", f4 = "x13", f4 = "x14",
                     f3 = "x08", f3 = "x09", f3 = "x10")
p2 <- set_cfa_layout(p,
                    indicator_order = indicator_order2,
                    fcov_curve = 1.5,
                    loading_position = .8)
plot(p2)

# Use automatically generated indicator_order and indicator_factor
p2 <- set_cfa_layout(p,
                    fcov_curve = 1.5,
                    loading_position = .8)
plot(p2)

p2 <- set_cfa_layout(p, indicator_order,
                         indicator_factor,
                         fcov_curve = 1.5,
                         loading_position = .8,
                         point_to = "left")
plot(p2)
p2 <- set_cfa_layout(p, indicator_order,
                         indicator_factor,
                         fcov_curve = 1.5,
                         loading_position = .8,
                         point_to = "up")
plot(p2)
p2 <- set_cfa_layout(p, indicator_order,
                         indicator_factor,
                         fcov_curve = 1.5,
                         loading_position = .8,
                         point_to = "right")
plot(p2)