get_prior_SEM {EMC2} | R Documentation |
Prior specification or prior sampling for SEM estimation.
get_prior_SEM(
prior = NULL,
n_pars = NULL,
sample = TRUE,
N = 1e+05,
selection = "mu",
design = NULL,
Lambda_mat = NULL,
B_mat = NULL,
K_mat = NULL,
G_mat = NULL,
covariates = NULL
)
prior |
A named list containing the prior mean on group-level mean (theta_mu_mean), variance of group-level mean (theta_mu_var), variance of the loadings and G (lambda_var), variance of the latent regressions and (B_var), shape and rate prior on the factor variances (a_p and b_p), and shape and rate prior on the residual variances (a_e and b_e) |
n_pars |
Argument used by the sampler, best left NULL. In user case inferred from the design |
sample |
Whether to sample from the prior. Default is TRUE. If not returns a prior list |
N |
How many samples to draw from the prior, default 1e5 |
selection |
Which parameter type to select e.g. |
design |
The design obtained from |
Lambda_mat |
The loadings constraint matrix |
B_mat |
The latent regressions constraint matrix |
K_mat |
The regression on the parameters by the included covariates |
G_mat |
The regression on the latent factors by the included covariates |
covariates |
The included covariates |
A list with a single entry of type of samples from the prior (if sample = TRUE) or else a prior object