update_gamma_alpha_subid_separate_tau: Update gamma and alpha together. Update the variational mean...

In zhenkewu/lotR: Latent class analysis with Observed Trees in R (lotR)

Update gamma and alpha together. Update the variational mean and variance for logit of class-specific response probabilities (for the s_u=1 component)

Description

separate tau's

Usage

update_gamma_alpha_subid_separate_tau(
  u,
  g_psi,
  g_phi,
  tau_2_t_u,
  tau_1_t_u,
  E_beta,
  E_zeta_u,
  X,
  E_eta,
  E_xi_u,
  rmat,
  h_pau,
  levels,
  subject_ids,
  v_lookup
)

Arguments

u	node id (internal or leaf node
g_psi, g_phi	g of local variational parameters
tau_2_t_u, tau_1_t_u	variational Gaussian variances for gamma and alpha
E_beta, E_zeta_u	moment updates produced by get_moments_cpp; E_zeta_u is directly calculated: prob[u]*sigma_gamma[u,,]
X	transformed data: 2Y-1
E_eta	leaves' expected eta
E_xi_u	node u's expected xi
rmat	a matrix of variational probabilities of all observations belong to K classes; N by K; each row sums to 1
h_pau	a numeric vector of length p indicating the branch length between a node and its parent
levels	a vector of possibly repeating integers from 1 to Fg, or L,
subject_ids	the ids of subjects in the leaf descendants of node u
v_lookup	a vector of length equal to the total number of rows in X; each element is an integer, indicating which leaf does the observation belong to.

Value

a list

resA

actually 1/A in the paper, this is variance

resB

logresBsq_o_A

resC

actually 1/C in the paper, this is variance

resD

logresDsq_o_C

zhenkewu/lotR documentation built on April 24, 2022, 2:36 a.m.