run_glmeiv_random_init_simulatr: Run GLM-EIV (random inititalization)

In timothy-barry/glmeiv: Implements the GLM-EIV model and method

Run GLM-EIV (random inititalization)

Description

Runs GLM-EIV using random initializations for the parameters. Currently, the function assumes that there is (at most) a single covariate term.

Usage

run_glmeiv_random_init_simulatr(
  dat,
  m_fam,
  g_fam,
  covariate_matrix,
  m_offset,
  g_offset,
  alpha = 0.95,
  n_em_rep = 15,
  save_membership_probs_mult = 250,
  pi_guess_range = c(1e-05, 0.03),
  m_perturbation_guess_range = log(c(0.1, 1.5)),
  g_perturbation_guess_range = log(c(0.5, 10)),
  m_intercept_guess_range = log(c(1e-04, 0.1)),
  g_intercept_guess_range = log(c(1e-04, 0.1)),
  m_covariate_coefs_guess_range = log(c(0.25, 2)),
  g_covariate_coefs_guess_range = log(c(0.25, 2)),
  exponentiate_coefs = FALSE
)

Arguments

dat	a data frame containing columns m, g
m_fam	family describing m
g_fam	family describing g
covariate_matrix	the matrix of covariates; NULL if there are no covariates.
m_offset	offsets for m
g_offset	offsets for g
alpha	CIs returned at level (1-alpha)%
n_em_rep	number of EM replicates
save_membership_probs_mult	save membership probabilities at this multiple
pi_guess_range	range of values over which to sample pi
m_perturbation_guess_range	range of values over which to sample m_perturbation
g_perturbation_guess_range	range of values over which to sample g_perturbation
m_intercept_guess_range	range over which to sample m_intercept
g_intercept_guess_range	range over which to sample g_intercept
m_covariate_coefs_guess_range	range over which to sample m_covariate_coefs
g_covariate_coefs_guess_range	range over which to sample g_covariate_coefs
exponentiate_coefs	(boolean) should the estimated coefficients (and CIs) be exponentiated?

Value

a fitted GLM-EIV object

Examples

# A simpler Gaussian example
m_fam <- g_fam <- gaussian() %>% augment_family_object()
n <- 20000
B <- 2
pi <- 0.05
m_intercept <- 1
m_perturbation <- -2
g_intercept <- -1
g_perturbation <- 2
m_offset <- g_offset <- NULL
covariate_matrix <- data.frame(batch = rbinom(n = n, size = 1, prob = 0.5))
m_covariate_coefs <- g_covariate_coefs <- 0.5
dat <- generate_full_data(m_fam = m_fam, m_intercept = m_intercept,
m_perturbation = m_perturbation, g_fam = g_fam, g_intercept = g_intercept,
g_perturbation = g_perturbation, pi = pi, n = n, B = B,
covariate_matrix = covariate_matrix, m_covariate_coefs = m_covariate_coefs,
g_covariate_coefs = g_covariate_coefs, m_offset = m_offset, g_offset = g_offset)[[1]]
fit <- run_glmeiv_random_init_simulatr(dat = dat, m_fam = m_fam, g_fam = g_fam,
covariate_matrix = NULL, m_offset = NULL, g_offset = NULL)

timothy-barry/glmeiv documentation built on Jan. 30, 2024, 3:46 p.m.