UpdateTheta_BrainMap: Parameter Estimates in EM Algorithm for Bayesian brain map

Description

Parameter Estimates in EM Algorithm for Bayesian brain map

Usage

UpdateTheta_BrainMap.spatial(
  prior_mean,
  prior_var,
  meshes,
  BOLD,
  theta,
  C_diag,
  H,
  Hinv,
  s0_vec,
  D,
  Dinv_s0,
  verbose = FALSE,
  return_MAP = FALSE,
  update = c("all", "kappa", "A")
)
UpdateTheta_BrainMap.independent(
  prior_mean,
  prior_var,
  BOLD,
  theta,
  C_diag,
  H,
  Hinv,
  update_nu0sq = TRUE,
  return_MAP = FALSE,
  verbose = TRUE
)

Value

An updated list of parameter estimates, theta, OR if return_MAP=TRUE, the posterior mean and precision of the latent fields

Arguments

prior_mean: (\(V \times Q\) matrix) mean maps for each network in prior
prior_var: (\(V \times Q\) matrix) between-subject variance maps for each network in prior
meshes: NULL for spatial independence model, otherwise a list of objects of class "BrainMap_mesh" containing the triangular mesh (see make_mesh) for each brain structure.
BOLD: (\(V \times Q\) matrix) dimension-reduced fMRI data
theta: (list) current parameter estimates
C_diag: \((Qx1)\) diagonal elements of residual covariance after dimension reduction
H, Hinv: For dimension reduction
s0_vec: Vectorized prior means
D: Sparse diagonal matrix of prior standard deviations
Dinv_s0: The inverse of D times s0_vec
verbose: If TRUE, display progress of algorithm. Default: FALSE.
return_MAP: If TRUE. return the posterior mean and precision of the latent fields instead of the parameter estimates. Default: FALSE.
update: Which parameters to update. Either "all", "A" or "kappa".
update_nu0sq: For non-spatial model: updating nu0sq is recommended if dimension reduction was not performed, and is not recommended if it was.