Mico_bi_lasso {lnmCluster}R Documentation

Penalized Logistic Normal Multinomial factor analyzer main estimation process

Description

Main function will perform PLNM factor analyzer and return parameters

Usage

Mico_bi_lasso(
  W_count,
  G,
  Q_g,
  pi_g,
  mu_g,
  sig_g,
  V,
  m,
  B_K,
  T_K,
  D_K,
  cov_str,
  tuning,
  iter,
  const,
  beta_g,
  X
)

Arguments

W_count

The microbiome count matrix

G

All possible number of components. A vector.

Q_g

A specific number of latent dimension.

pi_g

A vector of initial guesses of component proportion

mu_g

A list of initial guess of mean vector

sig_g

A list of initial guess of covariance matrix for each component

V

A list of initial guess of variational varaince

m

A list of initial guess of variational mean

B_K

A list of initial guess of loading matrix.

T_K

A list of identity matrix with dimension q.

D_K

A list of initial guess of error matrix

cov_str

The covaraince structure you choose, there are 2 different models belongs to this family:UUU and GUU. You can choose more than 1 covarance structure to do model selection.

tuning

length G vector with range 0-1, define the tuning parameter for each component

iter

Max iterations, default is 150.

const

the permutation constant in multinomial distribution. Calculated before the main algorithm in order to save computation time.

beta_g

initial guess of covariates coefficients.

X

The regression covariates matrix, which generates by model.matrix.

Value

z_ig Estimated latent variable z

cluster Component labels

mu_g Estimated component mean

pi_g Estimated component proportion

B_g Estimated sparsity loading matrix

D_g Estimated error covariance

COV Estimated component covariance

beta_g Estimated covariates coefficients.

overall_loglik Complete log likelihood value for each iteration

ICL ICL value

BIC BIC value

AIC AIC value

tuning display the tuning parameter you specified.


[Package lnmCluster version 0.3.1 Index]