simulate_lmmelsm: Simulate data from latent uni/multidimensional MELSM

Description

Simulate data from latent uni/multidimensional MELSM

Usage

simulate_lmmelsm(
  n,
  K,
  lambda,
  resid,
  nu,
  mu_beta = NULL,
  logsd_beta = NULL,
  P_random_ind = NULL,
  Q_random_ind = NULL,
  mu_logsd_betas_cor,
  mu_logsd_betas_sigma,
  epsilon_cor,
  zeta = NULL,
  X_loc = NULL,
  X_sca = NULL,
  X_bet = NULL,
  L2_pred_only = FALSE
)

Value

List of params (list), data (list), and df (data.frame).

Arguments

n: Integer. Number of repeated observations per group.
K: Integer. Number of groups.
lambda: Matrix (FxJ). Loading matrix.
resid: Numeric vector (J). Residual SDs.
nu: Numeric vector (J). Intercepts.
mu_beta: Matrix (PxF). Location coefficient matrix.
logsd_beta: Matrix (QxF). Scale coefficient matrix.
P_random_ind: Integer vector (P_random). Which location predictors have random slopes.
Q_random_ind: Integer vector (Q_random). Which scale predictors have random slopes.
mu_logsd_betas_cor: Matrix (Symmetric, SPD; F2 + P_randomF + Q_random*F). Correlation matrix of random effects (slopes and intercepts, for location and scale models).
mu_logsd_betas_sigma: Numeric vector (Positive; F2 + P_randomF + Q_random*F). RE SDs (intercepts on exponentiated scale, if zeta is specified).
epsilon_cor: Matrix (Symmetric, SPD; F). Stochastic error term correlation between factors.
zeta: Matrix (Rx[F*2 + P_random*F + Q_random*F]). Coefficient matrix for predicting RE SDs.
X_loc: Matrix (Optional; NxP). Location design matrix.
X_sca: Matrix (Optional; NxQ). Scale design matrix.
X_bet: Matrix (Optional; NxR). Between-SD design matrix.
L2_pred_only: Logical. Whether predictors should be group-level (TRUE) or observation level (FALSE).

Author

Stephen R. Martin