mi_bootstrap: mi_bootstrap

In jpkrooney/rcorex: An Implementation of Total Correlation Explanation

mi_bootstrap

Description

Internal function to calculate bias and sd of MIS via bootstrap

Usage

mi_bootstrap(
  data,
  marginal_description,
  theta,
  log_p_y,
  p_y_given_x_3d,
  dim_visible,
  smooth_marginals,
  n_permutes = 20,
  logpx_method
)

Arguments

data	Data provided by user
marginal_description	Character string which determines the marginal distribution of the data.
theta	List of estimated parameters
log_p_y	A 2D matrix representing the log of the marginal probability of the latent variables
p_y_given_x_3d	A 3D array of numerics in range (0, 1), that represent the probability that each observed x variable belongs to n_hidden latent variables of dimension dim_hidden. p_y_given_x_3d has dimensions (n_hidden, n_samples, dim_hidden).
dim_visible	The dimension of the data provided in data - i.e. the number of discrete levels that exist in the data. Must be positive integer.
smooth_marginals	Boolean (TRUE/FALSE) which indicates whether Bayesian smoothing of marginal estimates should be used.
n_permutes	numeric to specify number of bootstrap estimates to calculate. Default = 20
logpx_method	EXPERIMENTAL - A character string that controls the method used to calculate log_p_xi. "pycorex" uses the same method as the Python version of biocorex, "mean" calculates an estimate of log_p_xi by averaging across n_hidden estimates.

Value

Returns a list

jpkrooney/rcorex documentation built on July 25, 2022, 1:37 a.m.