lavinteract (version 0.3.5)

lav_slopes: Simple slopes and interaction plots for fitted 'lavaan' models

Description

Computes conditional (simple) slopes of a focal predictor across values of a moderator from a fitted 'lavaan' model that includes their explicit product term. Plots predicted lines with Wald confidence ribbons, and print an APA-style test of the interaction for easy reporting and interpretation, plus a simple-slopes table.

Usage

lav_slopes(
  fit,
  outcome,
  pred,
  modx,
  interaction,
  data = NULL,
  modx.values = NULL,
  modx.labels = NULL,
  pred.range = NULL,
  conf.level = 0.95,
  x.label = NULL,
  y.label = NULL,
  legend.title = NULL,
  colors = NULL,
  line.size = 0.80,
  alpha = 0.20,
  table = TRUE,
  digits = 2,
  modx_n_unique_cutoff = 4L,
  return_data = FALSE
)
# S3 method for lav_slopes
print(x, ...)
# S3 method for lav_slopes
summary(object, ...)

Value

A list with elements:

plot

ggplot object with lines and confidence ribbons.

slope_table

Data frame with moderator levels, simple slopes, SE, z, and CI.

plot_data

Only when return_data = TRUE: data used to build the plot.

Arguments

fit

A fitted 'lavaan' object that includes the product term (required).

outcome

Character. Name of the dependent variable in fit (required).

pred

Character. Name of the focal predictor whose simple slopes are probed (required).

modx

Character. Name of the moderator (required).

interaction

Character. Name of the product term in fit (e.g., "X_Z") (required).

data

data.frame. Raw data. If NULL, the function tries to pull data from fit via lavInspect.

modx.values

Numeric or character vector. Values or levels of the moderator at which to compute slopes; derived automatically when NULL.

modx.labels

Character vector. Legend/table labels for modx.values (default: the character form of modx.values).

pred.range

Numeric length-2. Range c(min, max) for the x-axis; uses observed range in data when available, else c(-2, 2).

conf.level

Numeric in (0,1). Confidence level for CIs and ribbons (default: 0.95).

x.label

Character. X-axis label (default: pred).

y.label

Character. Y-axis label (default: outcome).

legend.title

Character. Legend title; if NULL, the legend shows only levels (default: NULL).

colors

Character vector. Colors for lines and ribbons; named vector recommended with names matching modx.labels (default: Okabe-Ito palette).

line.size

Numeric > 0. Line width (default: 0.80).

alpha

Numeric in (0,1). Ribbon opacity (default 0.20).

table

Logical. Print APA-style interaction test and simple-slopes table (default: TRUE).

digits

Integer >= 0. Decimal digits in printed output (default: 2).

modx_n_unique_cutoff

Integer >= 1. Threshold for treating a numeric moderator as continuous and using mean ± SD (default: 4).

return_data

Logical. If TRUE, include the plotting data.frame in the returned list (default: FALSE).

x

A 'lav_slopes' object.

...

Additional arguments; unused.

object

A 'lav_slopes' object.

Notes

Estimates are unstandardized; a standardized beta for the interaction is also reported for reference. Wald tests assume large-sample normality of estimates.

Details

The model should include a main effect for the predictor, a main effect for the moderator, and their product term. The simple slope of the predictor at a given moderator value combines the predictor main effect with the interaction term. The moderator can be continuous or categorical. Standard errors use the delta method with the model covariance matrix of the estimates.

Examples

set.seed(42)
X <- rnorm(100); Z <- rnorm(100); X_Z <- X*Z
Y <- 0.6*X + 0.6*Z + 0.3*X_Z + rnorm(100, sd = 0.7) 
dataset <- data.frame(Y, X, Z, X_Z)
fit <- lavaan::sem("Y ~ X + Z + X_Z", data = dataset)
lav_slopes(
fit = fit, 
data = dataset,
outcome = "Y", 
pred = "X", 
modx = "Z", 
interaction = "X_Z")