Tests the robustness of factor-OU convergence findings by randomly permuting the Y factor space and re-estimating the model. Generates empirical null distribution for convergence statistics.
test_permutation_robustness(
factors_data,
data_prep,
n_perms = 100,
seed = 123,
use_stan = TRUE,
chains = 4,
iter = 2000,
verbose = TRUE
)List with components:
observed_lambdaOriginal mean-reversion speeds.
null_distributionMatrix of permutation-based lambda values.
p_valuesOne-sided p-values for each factor.
significantLogical vector indicating significance at alpha = 0.05.
effect_sizeStandardized effect sizes (z-scores).
Data frame with factor information
Prepared data object
Number of permutations (default: 100)
Random seed for reproducibility (default: 123)
Logical, use Stan for estimation (default: TRUE)
Number of MCMC chains (default: 4)
Number of MCMC iterations (default: 2000)
Logical; print progress and diagnostic information. Default TRUE.
(too slow for many iterations).