Centrality-stability coefficient (case-dropping subset bootstrap)

Usage

net_stability(
  data,
  method = "glasso",
  measures = c("strength", "expected_influence"),
  centrality_fn = NULL,
  drop_prop = seq(0.1, 0.9, by = 0.1),
  iter = 100L,
  threshold = 0.7,
  certainty = 0.95,
  labels = NULL,
  estimator_args = list(),
  ...
)

Arguments

data: Data frame or matrix (rows = observations), resampled exactly as given (see net_boot()).
method: Estimator (see psychnet()). Default "glasso".
measures: Centrality measures to assess. Defaults to the two recommended for psychometric networks (c("strength", "expected_influence")); "betweenness"/"closeness" and custom measures (via centrality_fn) are also accepted. See net_centralities().
centrality_fn: Optional function supplying any non-built-in measures (see net_centralities()).
drop_prop: Proportions of cases to drop. Default seq(0.1, 0.9, 0.1).
iter: Subsets per proportion. Default 100.
threshold: Minimum acceptable rank correlation. Default 0.7.
certainty: Probability the correlation must exceed threshold. Default 0.95.
labels: Optional node labels.
estimator_args: Named list of estimator arguments. Use this for names consumed by the stability diagnostic itself, such as estimator threshold.
...: Passed to the estimator.

Value

An object of class psychnet_stability with $cs (CS-coefficient per measure) and a tidy $table (columns measure, drop_prop, mean_cor, sd_cor, prop_above) of the case-dropping correlations by drop proportion. Visualise it with plot.psychnet_stability().

Examples

set.seed(1)
x <- matrix(stats::rnorm(200 * 5), 200, 5) %*% chol(0.4^abs(outer(1:5, 1:5, "-")))
colnames(x) <- paste0("V", 1:5)
# method = "pcor" and small iter keep this example fast; the "glasso"
# default and iter = 100 are what a real analysis should use.
cs <- net_stability(x, method = "pcor", drop_prop = c(0.3, 0.6), iter = 10)
cs$cs
#>           strength expected_influence 
#>                  0                  0