nl_het: Cluster heterogeneity in nonlinear effects
In MultiSpline: Spline-Based Nonlinear Modeling for Multilevel and Longitudinal Data

nl_het

R Documentation

Cluster heterogeneity in nonlinear effects

Quantifies and visualises how much the nonlinear relationship between x and y varies across clusters, using a model with random spline slopes.

The function:

Refits the model with random spline slopes (if not already fitted with random_slope = TRUE).
Extracts cluster-specific predicted curves (BLUPs).
Returns a heterogeneity summary: variance of slopes across clusters at each x value, and a plot of the cluster-specific trajectories.
Performs a likelihood-ratio test comparing the random-slope model against a random-intercept-only model to assess whether heterogeneity is statistically significant.

nl_het(
  object,
  n_clusters_plot = 30L,
  x_seq = NULL,
  level = 0.95,
  plot = TRUE,
  seed = 42L
)

`object`	An `nl_fit` object fitted with a single `cluster` variable (and either `random_slope = TRUE` or `FALSE`; in the latter case the model is refit internally).
`n_clusters_plot`	Maximum number of cluster curves to display in the trajectory plot. Default `30L`. Use `Inf` for all clusters.
`x_seq`	Optional numeric vector of x values for prediction.
`level`	Confidence level for the population-mean ribbon. Default `0.95`.
`plot`	Logical; print the trajectory plot. Default `TRUE`.
`seed`	Integer seed for reproducibility when sub-sampling clusters. Default `42L`.

A list (invisibly) with:

trajectory_df: Long data frame of cluster-specific predicted values.
slope_variance: Named numeric: SD of first-derivative estimates across clusters at each x value.
lrt: LRT comparing random-slope vs random-intercept model (NULL if random_slope = TRUE was supplied).
plot: A ggplot object.