onestep TMLE of average density parameter

onestep TMLE of average density parameter

onestep TMLE of average density parameter

Format

R6Class object.

Value

Object of R6Class with methods

Methods

new(x, epsilon_step = NULL, verbose = NULL)

specify data; define targeting step size

fit_density(bin_width = .1, lambda_grid)

use `cvDensityHAL` to fit density. bin_width for pre-binning of continuous x; lambda_grid for grid search of lambda in HAL

Public fields

x

random sample from distribution

p_hat

(empiricalDensity) containing density estimates

Psi

paramter value

EIC

vector of EIC

epsilon_step

step size for one-step targeting

CI

(numeric vector) length 2; lower + upper CI

longDataOut

(longiData) for transforming x into longitudinal format dataframe

HAL_tuned

(hal9001) generated by cvDensityHAL class.

Methods

Public methods

• avgDensityTMLE$new()

• avgDensityTMLE$fit_density()

• avgDensityTMLE$fit_density_pen_likeli()

• avgDensityTMLE$compute_Psi()

• avgDensityTMLE$compute_EIC()

• avgDensityTMLE$update_once()

• avgDensityTMLE$target_onestep()

• avgDensityTMLE$inference()

• avgDensityTMLE$compute_min_phi_ratio()

• avgDensityTMLE$clone()

---

Method new()

Usage

avgDensityTMLE$new(x, epsilon_step = NULL, verbose = NULL)

---

Method fit_density()

Usage

avgDensityTMLE$fit_density(
  bin_width = 0.1,
  lambda_grid = NULL,
  M = NULL,
  n_fold = 3,
  ...
)

---

Method fit_density_pen_likeli()

Usage

avgDensityTMLE$fit_density_pen_likeli(
  bin_width = 0.1,
  lambda_grid = NULL,
  lambda_min_ratio = NULL,
  n_fold = 3,
  ...
)

---

Method compute_Psi()

Usage

avgDensityTMLE$compute_Psi(p_hat, to_return = FALSE)

---

Method compute_EIC()

Usage

avgDensityTMLE$compute_EIC(p_hat, Psi, to_return = FALSE)

---

Method update_once()

Usage

avgDensityTMLE$update_once()

---

Method target_onestep()

Usage

avgDensityTMLE$target_onestep(verbose = FALSE)

---

Method inference()

Usage

avgDensityTMLE$inference()

---

Method compute_min_phi_ratio()

Usage

avgDensityTMLE$compute_min_phi_ratio()

---

Method clone()

The objects of this class are cloneable with this method.

Usage

avgDensityTMLE$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# avgDensityTMLE$new()